INDEX

Explanations

code snippets, especially those mentioning content types, URLs, paths, and regular expressions.

oai_token-act-pair · gemini-2.0-flash

code string extraction

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bir

-0.56

št

-0.48

 similar

-0.48

str

-0.43

 Similar

-0.43

Similar

-0.43

bir

-0.43

 दौरान

-0.40

 Further

-0.39

leiding

-0.39

POSITIVE LOGITS

ViewFeatures

0.85

UserScript

0.81

 UnityEditor

0.75

 otomatig

0.75

tvguidetime

0.72

 typelib

0.72

 createContext

0.72

 IndexError

0.71

 MainAxisSize

0.71

 Greenland

0.70

Activations Density 1.316%

code snippets, especially those mentioning content types, URLs, paths, and regular expressions.

code string extraction

No Comments

No Known Activations