INDEX

Explanations

a variety of domain-specific terminology across distinct topics like manufacturing, computer science, agriculture and travel.

oai_token-act-pair · gemini-2.0-flash

manufacturing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 AppCompatTheme

-0.69

ForResult

-0.62

 fédé

-0.58

 médec

-0.56

 cérami

-0.55

 compéti

-0.54

 êtres

-0.53

competitive

-0.52

']")

-0.52

POSITIVE LOGITS

<bos>

0.96

 للمعارف

0.59

Бахар

0.54

Gambas

0.46

Aiheesta

0.46

 Référence

0.45

Билгалдахарш

0.44

OGND

0.44

日閲覧

0.44

FunctionFlags

0.44

Activations Density 12.679%

a variety of domain-specific terminology across distinct topics like manufacturing, computer science, agriculture and travel.

manufacturing

No Comments

No Known Activations