INDEX

Explanations

python code, specifically dunder methods (init, iter, etc.) and related keywords

oai_token-act-pair · gemini-2.0-flash

__

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

&_

-0.57

_=

-0.50

}}=$

-0.49

initialValue

-0.47

Jef

-0.47

 initial

-0.46

 Brésil

-0.46

 Lehmann

-0.45

 Editora

-0.45

POSITIVE LOGITS

Autoritní

1.04

ⓧ

0.94

 NSCoder

0.93

BeginContext

0.88

ParallelGroup

0.84

 unknownFields

0.80

migrationBuilder

0.79

DataAnnotations

0.79

protoc

0.78

GraphicsUnit

0.78

Activations Density 4.580%

python code, specifically dunder methods (__init__, __iter__, etc.) and related keywords

__

No Comments

No Known Activations

python code, specifically dunder methods (init, iter, etc.) and related keywords