INDEX

Explanations

javascript code

oai_token-act-pair · gemini-2.0-flash

code snippets

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

__(/*!

-0.65

acamata

-0.63

haviors

-0.60

 erlä

-0.59

 kasarigan

-0.58

glEnd

-0.58

الحياه

-0.58

最快更新

-0.56

laar

-0.56

 الحره

-0.56

POSITIVE LOGITS

 Daarom

0.46

ifera

0.44

iliger

0.44

 OSError

0.42

 Veel

0.42

 pressure

0.41

 raff

0.40

 longs

0.40

 wireType

0.40

orian

0.40

Activations Density 3.836%

javascript code

code snippets

No Comments

No Known Activations