INDEX

Explanations

code related Javascript exports and React components

oai_token-act-pair · gemini-2.0-flash

code

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

void

-0.52

 يتيمه

-0.47

ima

-0.46

 that

-0.44

ścią

-0.44

messageInfo

-0.44

cell

-0.44

 صوتيه

-0.44

ex

-0.43

function

-0.43

POSITIVE LOGITS

TagMode

0.73

kloped

0.65

 useRouter

0.63

 ModelRenderer

0.59

NamedQueries

0.56

mybatisplus

0.55

twimg

0.54

 '/':

0.54

 muualla

0.54

ControllerAdvice

0.54

Activations Density 1.030%

code related Javascript exports and React components

code

No Comments

No Known Activations