INDEX

Explanations

content related to government, politics or elections

oai_token-act-pair · gemini-2.0-flash

politics

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

Not in Any Lists

No Comments

Negative Logits

 gọn

-0.52

ير

-0.49

 Walkover

-0.47

ంలో

-0.46

 сна

-0.46

 Corporation

-0.45

getJSONArray

-0.44

 Garrett

-0.43

 ממש

-0.43

 Corp

-0.43

POSITIVE LOGITS

UserScript

0.84

+#+#

0.81

0.74

antMatchers

0.65

protoimpl

0.65

ⓧ

0.63

SBATCH

0.59

ControllerAdvice

0.59

TypedDataSet

0.55

ագրություններ

0.55

Activations Density 2.633%

content related to government, politics or elections

politics

No Comments

No Known Activations