INDEX

Explanations

code documentation including parameter and return type information

oai_token-act-pair · gemini-2.0-flash

return

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

xase

-0.68

Tikang

-0.65

CWE

-0.63

TemporalType

-0.63

:+:

-0.59

beelding

-0.57

 الحره

-0.57

 Italijanski

-0.56

 ModelExpression

-0.56

adaptiveStyles

-0.56

POSITIVE LOGITS

 "..\..\..\

0.52

exitRule

0.49

 load

0.47

numerusform

0.47

0.46

 '.')

0.45

load

0.44

ברים

0.44

 sami

0.44

@"/

0.44

Activations Density 1.164%

code documentation including parameter and return type information

return

No Comments

No Known Activations