INDEX

Explanations

code snippets and programming keywords, especially those related to defining list manipulations.

oai_token-act-pair · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

StoryboardSegue

-1.44

sizeCache

-1.27

InputBorder

-1.02

出版年

-1.02

Personensuche

-1.01

 AssemblyCulture

-0.99

SBATCH

-0.99

 ligiloj

-0.98

 AssemblyTitle

-0.98

saraba

-0.98

POSITIVE LOGITS

print

0.68

 print

0.66

is

0.65

 None

0.62

def

0.59

in

0.59

def

0.57

and

0.57

 True

0.57

0.56

Activations Density 0.343%

code snippets and programming keywords, especially those related to defining list manipulations.

code

No Comments

No Known Activations