INDEX

Explanations

a mixture of Japanese words related to software development and English words related to conflicts and war

oai_token-act-pair · gemini-2.0-flash

foreign languages and code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 auffi

-0.73

 iſt

-0.69

 ―――――

-0.69

 插图

-0.66

$_"

-0.65

SourceChecksum

-0.65

."));

-0.64

 IBRARY

-0.64

FlatAppearance

-0.64

Eſ

-0.63

POSITIVE LOGITS

 nødvendig

0.32

 aktivitet

0.31

ンプ

0.30

 infância

0.30

 gammel

0.29

 anledning

0.28

 gefährlich

0.27

ーム

0.27

 gangen

0.27

ール

0.27

Activations Density 0.099%

a mixture of Japanese words related to software development and English words related to conflicts and war

foreign languages and code

No Comments

No Known Activations