INDEX

Explanations

code snippets related to programming

oai_token-act-pair · gemini-2.0-flash

Code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

teel

-0.55

StreetMap

-0.55

Revenir

-0.54

 Hayek

-0.54

 willed

-0.54

adeloupe

-0.54

 torchvision

-0.54

FundMe

-0.54

BagConstraints

-0.53

сылкі

-0.53

POSITIVE LOGITS

As

0.58

AS

0.57

Somebody

0.52

These

0.52

But

0.51

Because

0.51

If

0.50

 ویکی‌پدی

0.50

Otherwise

0.50

Are

0.50

Activations Density 10.479%

code snippets related to programming

Code snippets

No Comments

No Known Activations