INDEX

Explanations

code, dates, versions, government entities, and chemical terms.

oai_token-act-pair · gemini-2.0-flash

Diverse, formal language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 social

-0.86

 services

-0.77

 human

-0.73

 Services

-0.69

 Human

-0.66

 Social

-0.66

Social

-0.63

social

-0.60

Services

-0.59

 sociales

-0.57

POSITIVE LOGITS

tvguidetime

1.05

脚注の使い方

0.98

 MainAxisSize

0.93

__':

0.85

 SwitchCompat

0.83

__":

0.83

NewUrlParser

0.81

 Monfieur

0.81

 doubtnut

0.81

 Forumite

0.79

Activations Density 1.109%

code, dates, versions, government entities, and chemical terms.

Diverse, formal language

No Known Activations