INDEX

Explanations

code snippets with the keyword 'return' or comments indicating errors

oai_token-act-pair · gemini-2.0-flash

Code/identifiers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

{~

-0.52

市

-0.49

つ

-0.48

 oraciones

-0.48

中

-0.47

番

-0.47

 dentaire

-0.45

thy

-0.44

 schia

-0.44

Errorf

-0.44

POSITIVE LOGITS

 EconPapers

0.92

 autorytatywna

0.91

IndentedString

0.86

 saites

0.81

Autoritní

0.80

 betweenstory

0.79

 referenties

0.77

MLLoader

0.75

 propOrder

0.74

UnsafeEnabled

0.71

Activations Density 0.863%

code snippets with the keyword 'return' or comments indicating errors

Code/identifiers

No Comments

No Known Activations