INDEX

Explanations

references to patent numbers

oai_token-act-pair · gemini-2.0-flash

patents and publications

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

 متعلقه

-1.05

 مرئيه

-0.75

évaluateur

-0.74

 kasarigan

-0.73

rungsseite

-0.72

CloseOperation

-0.70

OGND

-0.68

parsedMessage

-0.68

 indisponible

-0.64

 jScrollPane

-0.64

POSITIVE LOGITS

randomUUID

0.49

bootstrapcdn

0.48

 titolo

0.47

InputModule

0.44

PROLOG

0.44

chila

0.43

rollup

0.43

tivis

0.43

phazard

0.43

uresti

0.43

Activations Density 0.045%

references to patent numbers

patents and publications

No Comments

No Known Activations