INDEX

Explanations

hexadecimal code snippets and currency abbreviations

oai_token-act-pair · gemini-2.0-flash

words starting with J

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

WZ

-0.49

Према

-0.49

 BorderSide

-0.48

-0.47

oredCriteria

-0.46

ronesia

-0.45

urez

-0.45

 HomeScreen

-0.44

 Packs

-0.44

 ***!

-0.44

POSITIVE LOGITS

Joint

0.85

 Joint

0.85

 Johnson

0.84

 joint

0.81

Johnson

0.79

 Jews

0.79

JOINT

0.78

joint

0.77

 Jewish

0.76

 Junior

0.75

Activations Density 2.939%

hexadecimal code snippets and currency abbreviations

words starting with J

No Comments

No Known Activations