INDEX

Explanations

sections of academic papers and legal documents, especially appendices, sections, parts, and assumptions

oai_token-act-pair · gemini-2.0-flash

numbers

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

HasOne

-0.48

Geografi

-0.48

 зато

-0.48

 uintptr

-0.47

zuf

-0.46

 sement

-0.45

PullParser

-0.45

titud

-0.45

zwa

-0.45

Демографія

-0.44

POSITIVE LOGITS

ReusableCell

0.65

Geplaatst

0.62

 مفص

0.58

 CreateTagHelper

0.56

rungsseite

0.56

ConstraintMaker

0.55

 TextAppearance

0.54

참고

0.54

 BrowserModule

0.52

évaluateur

0.52

Activations Density 11.720%

sections of academic papers and legal documents, especially appendices, sections, parts, and assumptions

numbers

No Comments

No Known Activations