INDEX

Explanations

words related to categories or types

oai_token-act-pair · gemini-2.0-flash

kind

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

AxisAlignment

-0.63

참고

-0.60

 meanwhile

-0.58

FOOTNOTES

-0.55

Референце

-0.55

CURLOPT

-0.54

 تضيفلها

-0.54

ToScroll

-0.52

 provisoire

-0.51

ünstler

-0.49

POSITIVE LOGITS

 stuff

0.59

 pieces

0.57

Vidite

0.54

 Италијани

0.54

}}$\\

0.53

 piece

0.52

jdź

0.49

docker

0.49

ונים

0.49

Semif

0.48

Activations Density 1.224%

words related to categories or types

kind

No Comments

No Known Activations