INDEX

Explanations

a mix of formatting characters and some technical jargon

oai_token-act-pair · gemini-2.0-flash

Foreign languages/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

AccessorTable

-0.79

intios

-0.69

 Paglinawan

-0.62

parsedMessage

-0.60

DATABASES

-0.59

 HasFactory

-0.59

StructEnd

-0.59

kost

-0.57

 onlyOwner

-0.55

 doInBackground

-0.54

POSITIVE LOGITS

openzeppelin

0.57

OrNil

0.54

 chào

0.52

madas

0.51

doria

0.51

 Reverso

0.50

ész

0.49

 تضيفلها

0.48

zerű

0.47

 shui

0.47

Activations Density 6.757%

a mix of formatting characters and some technical jargon

Foreign languages/code

No Comments

No Known Activations