INDEX

Explanations

text related to computer code

oai_token-act-pair · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

}>{

-0.48

esistenza

-0.45

cookieParser

-0.45

ITECH

-0.44

 Cataloging

-0.44

amoan

-0.44

tuuri

-0.42

'>{

-0.41

Cons

-0.40

getContext

-0.40

POSITIVE LOGITS

 raisonnable

0.65

+:+

0.61

tangentMode

0.61

UnusedPrivate

0.60

 thiệu

0.59

omitempty

0.59

JvmStatic

0.58

TagHelper

0.57

estación

0.57

 esempi

0.57

Activations Density 3.908%

text related to computer code

code

No Comments

No Known Activations