INDEX

Explanations

details about a fictional show including character names, associated items, and abilities

oai_token-act-pair · gemini-2.0-flash

Japanese anime/manga context

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

hdessä

-0.51

ouds

-0.51

 térm

-0.51

PhysRevD

-0.49

 industriales

-0.47

 tropicales

-0.46

 engraçadas

-0.46

 fréqu

-0.45

 meille

-0.45

 préfé

-0.45

POSITIVE LOGITS

Diwedd

0.64

stateMutability

0.63

 nahilalakip

0.62

LookAnd

0.56

 Ceramby

0.55

Xna

0.54

 تحلیل

0.54

TokenName

0.52

amina

0.51

存于互联网档案馆

0.51

Activations Density 3.200%

details about a fictional show including character names, associated items, and abilities

Japanese anime/manga context

No Comments

No Known Activations