INDEX

Explanations

words related to politics and government, especially names and positions of power

oai_token-act-pair · gemini-2.0-flash

cabinet

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 defaultstate

-0.73

Carriera

-0.67

WebControls

-0.66

KommentareTeilen

-0.61

]")]

-0.60

ISupport

-0.59

 onOptions

-0.58

 ostavi

-0.57

tvguidetime

-0.54

Gemeinden

-0.54

POSITIVE LOGITS

 ministry

0.98

 ministerial

0.96

 Ministry

0.94

 Minister

0.93

 cabinet

0.90

 Cabinet

0.90

 minister

0.90

minist

0.88

 ministerio

0.84

 ministers

0.84

Activations Density 1.284%

words related to politics and government, especially names and positions of power

cabinet

No Comments

No Known Activations