INDEX

Explanations

the letter "A" followed by one or more letters

oai_token-act-pair · gemini-2.0-flash

A

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

UMBUS

-0.53

zeugung

-0.50

Bur

-0.47

ke

-0.47

Bat

-0.46

例文帳に追加

-0.44

-0.43

 namespace

-0.43

AccessorTable

-0.42

POSITIVE LOGITS

 itſelf

0.80

 myſelf

0.74

 Roskov

0.71

ſelf

0.69

Демографія

0.69

 ſche

0.69

 Theſe

0.68

ſelves

0.68

 Majefty

0.68

 dieß

0.65

Activations Density 0.549%

the letter "A" followed by one or more letters

A

No Comments

No Known Activations