INDEX

Explanations

locations, celebrations and government officials' announcements related to a specific region

oai_token-act-pair · gemini-2.0-flash

Period

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 للمعارف

-0.75

 Indians

-0.60

PreferredItem

-0.59

 становника

-0.59

 Atty

-0.58

 Indian

-0.57

DebuggerNonUser

-0.56

 createState

-0.55

 Earlier

-0.55

avor

-0.55

POSITIVE LOGITS

VersionUID

0.51

FontOfSize

0.48

 dátum

0.47

emplar

0.47

 Post

0.47

nestjs

0.45

mybatisplus

0.44

Post

0.43

GenerationType

0.43

 calendriers

0.43

Activations Density 7.766%

locations, celebrations and government officials' announcements related to a specific region

Period

No Comments

No Known Activations