INDEX

Explanations

HTML tags

oai_token-act-pair · gemini-2.0-flash

Code extracts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

kloped

-0.52

 form

-0.45

«

-0.43

 pour

-0.40

 thức

-0.40

Revenir

-0.39

Viited

-0.38

put

-0.38

南浔

-0.37

define

-0.37

POSITIVE LOGITS

sizeCache

0.80

 jadx

0.79

UrlResolution

0.77

AsUp

0.76

rawDesc

0.75

 Meksiku

0.75

__":

0.75

HideFlags

0.73

]")]

0.73

UnsafeEnabled

0.71

Activations Density 0.211%

HTML tags

Code extracts

No Comments

No Known Activations