INDEX

Explanations

words related to data analysis or science

oai_token-act-pair · gemini-2.0-flash

algorithms and weighting

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

">//

-0.66

AndEndTag

-0.65

ंदीखरीदारी

-0.62

EndInit

-0.59

 المعيارى

-0.56

 Newswire

-0.55

//$

-0.55

LElement

-0.54

!*\

-0.54

contentLoaded

-0.53

POSITIVE LOGITS

BASEPATH

0.65

 weighting

0.51

 subjectivity

0.48

 ModelExpression

0.47

getLogger

0.45

StreetMap

0.44

 дописавши

0.43

ítmény

0.42

tė

0.41

 beauty

0.41

Activations Density 2.625%

words related to data analysis or science

algorithms and weighting

No Comments

No Known Activations