> ## Documentation Index
> Fetch the complete documentation index at: https://docs.priorlabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> TabPFN-3 and later versions support up to 1,000,000 rows, subject to feature count and checkpoint/API limits.
> For large datasets, use per-estimator subsampling, e.g. inference_config={"SUBSAMPLE_SAMPLES": 100_000}, in TabPFNClassifier or TabPFNRegressor from tabpfn or tabpfn_client.
> Pass raw pandas DataFrames to fit and predict. Categorical strings/categories, raw text, and missing feature values are handled automatically; no manual integer/one-hot encoding, imputation, scaling, or outlier removal is needed.

# Unsupervised embeddings

> Get the transformer embeddings for the test data X.

<Info>
  Looking for usage documentation? Check out [Embeddings](/capabilities/embeddings).
</Info>

<div className="python-reference-heading">
  <h2 id="unsupervised-unsupervised-tabpfnunsupervisedmodel-get-embeddings">
    `TabPFNUnsupervisedModel.get_embeddings`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-extensions/blob/840c15a1848a986b39c85bc17efc61e0e377f983/src/tabpfn_extensions/unsupervised/unsupervised.py#L968" aria-label="View source for TabPFNUnsupervisedModel.get_embeddings"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Get the transformer embeddings for the test data `X`.

```python theme={null}
TabPFNUnsupervisedModel.get_embeddings(
    X: torch.tensor,
    per_column: bool = False,
) -> torch.tensor
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="unsupervised-unsupervised-tabpfnunsupervisedmodel-get-embeddings--x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type">torch.tensor</code> | Required | — |
  | <span id="unsupervised-unsupervised-tabpfnunsupervisedmodel-get-embeddings--per-column" /><code className="python-reference-parameter">per\_<wbr />column</code> | <code className="python-reference-type">bool</code> | `False` | — |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type">torch.tensor</code> | torch.Tensor of shape (n\_samples, embedding\_dim) |
</div>

***

<div className="python-reference-heading">
  <h2 id="unsupervised-unsupervised-tabpfnunsupervisedmodel-get-embeddings-underscore">
    `TabPFNUnsupervisedModel.get_embeddings_`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-extensions/blob/840c15a1848a986b39c85bc17efc61e0e377f983/src/tabpfn_extensions/unsupervised/unsupervised.py#L986" aria-label="View source for TabPFNUnsupervisedModel.get_embeddings_"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

***

<div className="python-reference-heading">
  <h2 id="unsupervised-unsupervised-tabpfnunsupervisedmodel-get-embeddings-per-column">
    `TabPFNUnsupervisedModel.get_embeddings_per_column`
  </h2>

  <a className="python-reference-source" href="https://github.com/PriorLabs/tabpfn-extensions/blob/840c15a1848a986b39c85bc17efc61e0e377f983/src/tabpfn_extensions/unsupervised/unsupervised.py#L997" aria-label="View source for TabPFNUnsupervisedModel.get_embeddings_per_column"><span aria-hidden="true">\</></span> View source <span aria-hidden="true">↗</span></a>
</div>

Alternative implementation for [`get_embeddings`](/api-reference/python/tabpfn-extensions/unsupervised/embeddings#unsupervised-unsupervised-tabpfnunsupervisedmodel-get-embeddings), where we get the embeddings for each column as a label
separately and concatenate the results. This alternative way needs more passes but might be more accurate.

```python theme={null}
TabPFNUnsupervisedModel.get_embeddings_per_column(
    X: torch.tensor,
) -> torch.tensor
```

**Parameters**

<div className="python-reference-table">
  | Parameter | Type | Default | Description |
  | - | - | - | - |
  | <span id="unsupervised-unsupervised-tabpfnunsupervisedmodel-get-embeddings-per-column--x" /><code className="python-reference-parameter">X</code> | <code className="python-reference-type">torch.tensor</code> | Required | — |
</div>

**Returns**

<div className="python-reference-table python-reference-returns">
  | Type | Description |
  | - | - |
  | <code className="python-reference-type">torch.tensor</code> | — |
</div>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.