INDEX

Explanations

the word "message" and related computer code terms

oai_token-act-pair · gemini-2.0-flash

message

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 noqa

-0.91

 Mercurio

-0.82

 ſmall

-0.75

enumii

-0.67

 Normdatei

-0.66

 Mitar

-0.66

Efq

-0.65

 EconPapers

-0.64

 Majefty

-0.61

 materna

-0.60

POSITIVE LOGITS

bu

0.46

win

0.42

HideFlags

0.42

bau

0.40

rem

0.40

Retention

0.40

form

0.40

 capital

0.39

 vertra

0.39

 form

0.38

Activations Density 2.050%

the word "message" and related computer code terms

message

No Comments

No Known Activations