INDEX

Explanations

code snippets, particularly from Python and PHP

oai_token-act-pair · gemini-2.0-flash

code

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

XtraReports

-0.43

addCriterion

-0.41

hasNext

-0.38

 igen

-0.38

 hason

-0.35

gen

-0.33

OrCreate

-0.33

 wireType

-0.33

ENDIF

-0.32

 tierra

-0.32

POSITIVE LOGITS

 TextAppearance

0.89

RenderAtEndOf

0.73

 الرياضيه

0.72

 שוליים

0.72

assies

0.68

IntoConstraints

0.66

出版年

0.65

welli

0.63

ollection

0.63

crollView

0.63

Activations Density 4.195%

code snippets, particularly from Python and PHP

code

No Comments

No Known Activations