INDEX

Explanations

math and code snippets

oai_token-act-pair · gemini-2.0-flash

technical documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 يتيمه

-0.56

NameInMap

-0.52

textTheme

-0.49

 下午

-0.48

RESUMEN

-0.48

CellStyle

-0.47

RESUMO

-0.47

 consultato

-0.46

amer

-0.46

Viited

-0.45

POSITIVE LOGITS

 ExecuteAsync

0.60

ergies

0.59

makeText

0.58

rils

0.55

TintMode

0.54

ngdoc

0.53

ffindor

0.52

othes

0.49

invokeLater

0.49

 OMITTED

0.49

Activations Density 0.481%

math and code snippets

technical documents

No Comments

No Known Activations