INDEX

Explanations

the word "hard"

oai_token-act-pair · gemini-2.0-flash

hard

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

AndEndTag

-0.63

enumi

-0.61

IndentedString

-0.60

 незавершена

-0.59

PerformLayout

-0.57

findpost

-0.57

HideFlags

-0.54

Vidite

-0.53

enumii

-0.53

 ddelweddau

-0.52

POSITIVE LOGITS

 core

0.54

COVER

0.53

 earned

0.52

URLEncoder

0.50

Top

0.50

core

0.49

敛

0.49

DoubleQuotes

0.48

LORE

0.48

 cover

0.48

Activations Density 0.531%

the word "hard"

hard

No Known Activations