INDEX

Explanations

code-related syntax like preprocessor directives, operators, and types, especially in C-like languages.

oai_token-act-pair · gemini-2.0-flash

code

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

<bos>

-0.65

StackNavigator

-0.60

образие

-0.59

stateProvider

-0.57

+#+#

-0.52

bleau

-0.51

 ditu

-0.50

ödie

-0.50

."),

-0.49

verläs

-0.46

POSITIVE LOGITS

脚注の使い方

0.85

ագրություններ

0.71

abestanden

0.66

 henvisninger

0.66

 EconPapers

0.64

ResumeLayout

0.63

AndroidJUnit

0.63

ManagedBean

0.63

ConstraintMaker

0.62

Aiheesta

0.60

Activations Density 8.075%

code-related syntax like preprocessor directives, operators, and types, especially in C-like languages.

code

No Comments

No Known Activations