INDEX

Explanations

the word "model" and words associated with models and systems like parameters, function, adaptation, etc

oai_token-act-pair · gemini-2.0-flash

model

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

enumii

-0.65

UnitTesting

-0.56

 habet

-0.54

Tikang

-0.52

 محفوظة

-0.51

 stát

-0.51

baly

-0.49

 courriel

-0.48

 recev

-0.48

 ujednoznacz

-0.48

POSITIVE LOGITS

 AssemblyCulture

0.60

dehyde

0.54

 calldata

0.54

ederos

0.54

<?=$

0.52

iocene

0.52

 vigne

0.51

Referências

0.51

 geomet

0.50

锈钢

0.50

Activations Density 5.661%

the word "model" and words associated with models and systems like parameters, function, adaptation, etc

model

No Comments

No Known Activations