INDEX

Explanations

words related to a particular domain.

oai_token-act-pair · gemini-2.0-flash

forms

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

 religieuse

-0.48

move

-0.47

 qualités

-0.46

usch

-0.46

 essais

-0.44

 uska

-0.44

el

-0.43

 élevées

-0.43

shall

-0.43

行

-0.43

POSITIVE LOGITS

ViewImports

0.83

 विश्वसनीयता

0.76

 Signalez

0.75

dafx

0.71

ImageContext

0.68

 ujednoznacz

0.65

 autorytatywna

0.63

ViewFeatures

0.63

_{-\

0.63

orteur

0.63

Activations Density 3.426%

words related to a particular domain.

forms

No Comments

No Known Activations