INDEX

Explanations

code-related terms such as author, import, class, and the number 32

oai_token-act-pair · gemini-2.0-flash

code metadata

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

’

-0.72

‘

-0.65

‘

-0.62

’

-0.54

’,

-0.53

.’

-0.52

?’

-0.52

 inmates

-0.52

!’

-0.50

,’

-0.49

POSITIVE LOGITS

berdayakan

0.63

Lycka

0.63

Glej

0.60

 AttributeSet

0.60

ParallelGroup

0.59

WritableDatabase

0.57

ContentAsync

0.55

AppMethodBeat

0.54

protoc

0.53

 HomeComponent

0.53

Activations Density 18.640%

code-related terms such as author, import, class, and the number 32

code metadata

No Comments

No Known Activations