INDEX

Explanations

text containing scientific data and studies.

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

Personensuche

-0.68

 opérateur

-0.56

modelBuilder

-0.55

setupUi

-0.54

elemField

-0.54

 nakalista

-0.53

GEBURTSDATUM

-0.52

 ModelExpression

-0.52

styleable

-0.50

 ExecuteAsync

-0.50

POSITIVE LOGITS

 communautaire

0.56

τουργ

0.53

 SPAR

0.47

dis

0.47

koz

0.46

 прошел

0.45

TabIndex

0.45

agu

0.45

ход

0.45

 فريبيس

0.45

Activations Density 15.657%

text containing scientific data and studies.

No Comments

No Known Activations