INDEX

Explanations

mentions of media like movies and television, and cultural references

oai_token-act-pair · gemini-2.0-flash

Roots

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

oredCriteria

-0.96

WebElementEntity

-0.89

脚注の使い方

-0.84

WriteLiteral

-0.79

adaptiveStyles

-0.66

Rüyada

-0.66

下载附件

-0.65

XMLSchema

-0.65

 Infórmanos

-0.65

 MainAxisSize

-0.64

POSITIVE LOGITS

Easy

0.43

 nacionales

0.42

 National

0.42

 Nationale

0.41

 Shuttle

0.41

 nasional

0.41

 Bowden

0.40

skj

0.40

 alene

0.39

 national

0.39

Activations Density 0.971%

mentions of media like movies and television, and cultural references

Roots

No Comments

No Known Activations