INDEX

Explanations

This

np_token-act-pair-logits · gemini-2.0-flash

This

np_max-act-logits · gemini-2.0-flash

references to historical treaties and wars (specifically related to 19th century European conflicts)

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Diwedd

-0.80

 виправивши

-0.73

Filmographie

-0.70

IsContent

-0.69

 utafitiHapana

-0.65

 везе

-0.64

 Италијани

-0.61

ichni

-0.60

tvguidetime

-0.60

migrationBuilder

-0.60

POSITIVE LOGITS

Scénario

0.48

怎么可能

0.48

mailto

0.47

miche

0.45

"/

0.44

liel

0.44

وارد

0.43

 specialising

0.43

ميم

0.42

el

0.42

Activations Density 1.715%

This

This

references to historical treaties and wars (specifically related to 19th century European conflicts)

No Comments

No Known Activations