INDEX

Explanations

connects related words, and negations.

oai_token-act-pair · gemini-2.0-flash

all or none

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

AndEndTag

-0.90

 kasarigan

-0.83

RenderAtEndOf

-0.81

IntoConstraints

-0.79

 مشين

-0.78

 snippetHide

-0.77

 myſelf

-0.75

脚注の使い方

-0.75

 poffible

-0.71

 ſeveral

-0.70

POSITIVE LOGITS

all

1.29

 none

0.99

ALL

0.94

All

0.90

all

0.88

All

0.86

 todos

0.78

 tất

0.77

 None

0.76

 almost

0.71

Activations Density 1.297%

connects related words, and negations.

all or none

No Comments

No Known Activations