INDEX

Explanations

numbers enclosed in parentheses

oai_token-act-pair · gemini-2.0-flash

digits

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ReusableCell

-0.92

contentLoaded

-0.81

 resourceCulture

-0.79

 ModelExpression

-0.78

principalColumn

-0.77

 AssemblyVersion

-0.77

makeConstraints

-0.77

SequentialGroup

-0.76

ftagPool

-0.75

apimachinery

-0.74

POSITIVE LOGITS

acyjnych

0.42

ХА

0.40

 Coates

0.39

يع

0.38

umd

0.38

 complete

0.37

oides

0.37

 Haddad

0.36

http

0.36

entee

0.35

Activations Density 0.266%

numbers enclosed in parentheses

digits

No Comments

No Known Activations