INDEX

Explanations

technical and scientific terms

oai_token-act-pair · gemini-2.0-flash

technical contexts

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

 betweenstory

-1.09

rungsseite

-0.96

 Meksiku

-0.88

UserScript

-0.79

SourceChecksum

-0.74

MessageOf

-0.71

 >=",

-0.67

 disambiguazione

-0.66

脚注の使い方

-0.66

utnik

-0.64

POSITIVE LOGITS

capa

0.56

IMPORTED

0.52

tų

0.50

addContainerGap

0.47

lectricité

0.45

 dele

0.43

jde

0.43

MLLoader

0.43

χαν

0.42

ographiques

0.42

Activations Density 2.279%

technical and scientific terms

technical contexts

No Comments

No Known Activations