INDEX

Explanations

code related terms such as javascript, npm commands, and css

oai_token-act-pair · gemini-2.0-flash

Code and programming

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

 nonatomic

-0.57

jav

-0.50

กก

-0.48

 intptr

-0.47

XmlAccessType

-0.47

inheritDoc

-0.46

RTRS

-0.46

спо

-0.46

ewon

-0.45

 zugelassen

-0.45

POSITIVE LOGITS

 propOrder

0.72

AutoScaleMode

0.66

 للمعارف

0.65

AnimationsModule

0.65

Datuak

0.64

bootstrapcdn

0.64

MetaObject

0.63

 cherchés

0.62

RenderAtEndOf

0.62

 تانيه

0.59

Activations Density 1.804%

code related terms such as javascript, npm commands, and css

Code and programming

No Comments

No Known Activations