INDEX

Explanations

taxpayer

np_max-act-logits · gemini-2.0-flash

language related to finances and government spending

oai_token-act-pair · gemini-2.0-flash

taxpayer

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

MENAFN

-0.89

ScopeManager

-0.88

fjspx

-0.87

gonic

-0.84

 MotionEvent

-0.83

\{\\

-0.78

tanleria

-0.77

AnimationsModule

-0.77

 himo

-0.76

IndentedString

-0.76

POSITIVE LOGITS

 taxpayer

0.75

 taxpayers

0.73

tax

0.61

Tax

0.48

0.47

Tax

0.46

tax

0.45

0.43

 tưởng

0.43

0.42

Activations Density 2.005%

taxpayer

language related to finances and government spending

taxpayer

No Comments

No Known Activations