INDEX

Explanations

emojis, musical symbols, and food-related words

oai_token-act-pair · gemini-2.0-flash

tomato emoji

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.63

 Púb

-0.57

memoized

-0.56

 fehlen

-0.56

MIDDLEWARE

-0.55

 Dernière

-0.54

plevel

-0.52

implements

-0.50

جغرافيا

-0.50

()],

-0.49

POSITIVE LOGITS

 EconPapers

0.74

ScopeManager

0.71

bootstrapcdn

0.57

Havolalar

0.55

 ModelExpression

0.54

 JMenuItem

0.53

Amicalement

0.51

 scratch

0.51

 nguoi

0.51

варь

0.50

Activations Density 2.404%

emojis, musical symbols, and food-related words

tomato emoji

No Comments

No Known Activations