INDEX

Explanations

names and titles of people related to US politics

oai_token-act-pair · gemini-2.0-flash

Political statements

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WebControls

-0.86

 betweenstory

-0.81

GraphicsUnit

-0.76

 BorderRadius

-0.74

 مرئيه

-0.64

expandindo

-0.64

鰭

-0.63

writeFieldEnd

-0.63

 photolibrary

-0.62

Loco

-0.62

POSITIVE LOGITS

 nakalista

0.73

 pointed

0.59

 said

0.59

وصف

0.46

pointed

0.45

 praised

0.45

ाहरण

0.44

at

0.44

 deemed

0.43

 criticised

0.43

Activations Density 1.586%

names and titles of people related to US politics

Political statements

No Comments

No Known Activations