INDEX

Explanations

mentions of magazine issues or editions

oai_token-act-pair · gemini-2.0-flash

4 or 8

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

出版年

-0.81

EndGlobalSection

-0.69

parsedMessage

-0.63

poons

-0.62

GraphicsUnit

-0.61

ArgsConstructor

-0.59

EDEFAULT

-0.57

FilterChain

-0.57

encodeWith

-0.57

´)

-0.56

POSITIVE LOGITS

chaqueta

0.51

 acceptez

0.50

 transférez

0.50

 meille

0.50

 yourselves

0.46

 Mexicana

0.45

 Monfieur

0.45

 espoir

0.45

Efq

0.43

 distributed

0.43

Activations Density 0.630%

mentions of magazine issues or editions

4 or 8

No Comments

No Known Activations