INDEX

Explanations

hexadecimal character codes

oai_token-act-pair · gemini-2.0-flash

Hexadecimal/unicode sequences

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 Drapeau

-0.52

zionali

-0.48

PACE

-0.44

cashire

-0.44

ppon

-0.44

SOV

-0.44

written

-0.43

ricular

-0.43

utsche

-0.43

ø

-0.42

POSITIVE LOGITS

LookAnd

0.82

 oprot

0.71

 désolés

0.70

Бахар

0.68

StreetMap

0.68

MigrationBuilder

0.68

 LoggerFactory

0.66

SharedCtor

0.66

تفصیلات

0.65

 numerus

0.63

Activations Density 1.975%

hexadecimal character codes

Hexadecimal/unicode sequences

No Comments

No Known Activations