INDEX

Explanations

java code

oai_token-act-pair · gemini-2.0-flash

parenthesis

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ranton

-0.54

fromnode

-0.52

 Erişim

-0.52

enschappelijke

-0.50

iecie

-0.49

bbons

-0.49

<",

-0.49

-------------</

-0.48

 podjela

-0.48

structors

-0.47

POSITIVE LOGITS

OGND

0.60

MemoryWarning

0.57

 perfons

0.56

isinstance

0.54

 WebDriverWait

0.52

 CommonModule

0.51

Esto

0.50

 Majefty

0.50

Obrigado

0.50

 éduc

0.49

Activations Density 7.217%

java code

parenthesis

No Comments

No Known Activations