INDEX

Explanations

java code syntax

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 jButton

-0.54

 InputDecoration

-0.54

ΗΣ

-0.43

backtracking

-0.42

charCodeAt

-0.42

 samfun

-0.40

:^{

-0.40

-0.39

unwrap

-0.39

ката

-0.39

POSITIVE LOGITS

MENAFN

0.86

afficheront

0.86

 Monfieur

0.78

^(@)

0.77

 Houſe

0.75

 समीक्षक

0.74

Personendaten

0.74

 Theſe

0.72

Efq

0.72

kuuta

0.72

Activations Density 6.536%

java code syntax

code

No Comments

No Known Activations