INDEX

Explanations

date-like strings

oai_token-act-pair · gemini-2.0-flash

code data logs

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

Not in Any Lists

No Comments

Negative Logits

codable

-0.53

örté

-0.46

 Sabha

-0.42

ism

-0.42

hematical

-0.42

qvist

-0.40

idential

-0.39

 Berthe

-0.39

umbus

-0.39

ując

-0.39

POSITIVE LOGITS

MLLoader

0.84

évaluateur

0.79

 שוליים

0.77

 autorytatywna

0.71

 JpaRepository

0.70

 BoxFit

0.68

Билгалдахарш

0.67

 дописавши

0.65

RectangleBorder

0.65

saraba

0.65

Activations Density 2.159%

date-like strings

code data logs

No Comments

No Known Activations