INDEX

Explanations

mathematical/scientific notation and terminology

oai_token-act-pair · gemini-2.0-flash

integers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 الرياضيه

-0.71

+#+#

-0.66

出版年

-0.61

ⓧ

-0.59

providedIn

-0.57

 ModelExpression

-0.57

ImageContext

-0.55

DoubleQuotes

-0.55

 nonatomic

-0.54

 protoimpl

-0.52

POSITIVE LOGITS

 Shakspeare

0.57

Política

0.54

Nachteile

0.52

 anfangen

0.51

política

0.50

Fazit

0.48

 formerly

0.48

 proverb

0.47

 Morphology

0.47

 Estilo

0.47

Activations Density 7.419%

mathematical/scientific notation and terminology

integers

No Comments

No Known Activations