INDEX

Explanations

code snippets

oai_token-act-pair · gemini-2.0-flash

code and abbreviations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

<bos>

-0.66

ReusableCell

-0.49

 потому

-0.44

Referències

-0.43

ArrowToggle

-0.43

ollectionView

-0.42

 uintptr

-0.42

 consultato

-0.42

__':

-0.42

Hentet

-0.41

POSITIVE LOGITS

[];

0.64

 iſt

0.61

 varandra

0.59

StartTag

0.58

EndTag

0.57

 оригіналу

0.57

 createSprite

0.57

 ComVisible

0.55

coaster

0.55

 Público

0.54

Activations Density 14.025%

code snippets

code and abbreviations

No Comments

No Known Activations