INDEX

Explanations

code snippets and associated programming terms

oai_token-act-pair · gemini-2.0-flash

pattern

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

存于互联网档案馆

-0.66

ArgumentParser

-0.58

expandindo

-0.52

Erreferentziak

-0.51

__':

-0.49

 précision

-0.49

 незавершена

-0.49

ngdoc

-0.49

 تضيفلها

-0.47

 EventArgs

-0.47

POSITIVE LOGITS

 pattern

0.78

 Pattern

0.76

Pattern

0.73

 patterns

0.73

pattern

0.72

PATTERN

0.71

 PATTERN

0.70

atterns

0.69

 Patterns

0.67

SourceChecksum

0.66

Activations Density 1.483%

code snippets and associated programming terms

pattern

No Comments

No Known Activations