INDEX

Explanations

a mix of code snippets and possible french language

oai_token-act-pair · gemini-2.0-flash

Non-English text

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

izr

-0.60

SourceChecksum

-0.59

NewGuid

-0.58

lusconi

-0.50

WriteAttribute

-0.49

Биография

-0.48

Madonna

-0.44

 Madonna

-0.43

ies

-0.43

TargetException

-0.41

POSITIVE LOGITS

Personensuche

0.95

 réfugi

0.76

 voren

0.71

 vPvB

0.67

 originaire

0.67

 précédents

0.67

Parcelize

0.67

 littéraire

0.65

rentices

0.65

twimg

0.64

Activations Density 0.643%

a mix of code snippets and possible french language

Non-English text

No Comments

No Known Activations