INDEX

Explanations

academic references and sources, including author names, publications, and studies

oai_token-act-pair · gemini-2.0-flash

academic papers

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

 succes

-0.42

 Succes

-0.41

INJ

-0.41

dé

-0.40

↘

-0.40

ty

-0.40

ķ

-0.39

fix

-0.38

]-'

-0.38

 VARI

-0.38

POSITIVE LOGITS

AddTagHelper

0.71

évaluateur

0.69

 '\\;'

0.66

 ddelweddau

0.66

styleable

0.65

ArrowToggle

0.64

didSet

0.60

aarrggbb

0.59

resaid

0.59

WriteTagHelper

0.59

Activations Density 16.474%

academic references and sources, including author names, publications, and studies

academic papers

No Comments

No Known Activations