INDEX

Explanations

technical jargon related to industrial communication protocols and systems.

oai_token-act-pair · gemini-2.0-flash

technical documents

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

 للمعارف

-0.66

kloped

-0.55

Iconic

-0.48

icae

-0.48

 disponibilités

-0.47

mocha

-0.46

География

-0.45

řeba

-0.45

 consenti

-0.45

mpe

-0.45

POSITIVE LOGITS

:✨

0.70

 виправивши

0.65

Suara

0.55

 TextInputType

0.53

 betweenstory

0.53

fice

0.52

Personensuche

0.51

SqlDataReader

0.51

rinth

0.50

 Galli

0.50

Activations Density 1.143%

technical jargon related to industrial communication protocols and systems.

technical documents

No Comments

No Known Activations