INDEX

Explanations

computer instructions and directory paths

oai_token-act-pair · gemini-2.0-flash

Code and file paths

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

DeleteBehavior

-0.77

XmlAccessType

-0.76

脚注の使い方

-0.65

LoadScene

-0.65

ſelf

-0.64

tvguidetime

-0.63

 Cæsar

-0.63

 myſelf

-0.60

NewGuid

-0.59

gameserver

-0.58

POSITIVE LOGITS

 intptr

0.59

setVerticalGroup

0.50

Erreferentziak

0.47

bete

0.47

 teks

0.46

altor

0.45

teks

0.45

 überw

0.45

ाष

0.44

intur

0.44

Activations Density 1.017%

computer instructions and directory paths

Code and file paths

No Comments

No Known Activations