INDEX

Explanations

words and phrases commonly used in business or formal reporting contexts.

oai_token-act-pair · gemini-2.0-flash

comma

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

–

-0.58

—

-0.56

—

-0.53

-0.52

−

-0.48

–

-0.46

--

-0.43

--

-0.43

,-

-0.41

,-\

-0.40

POSITIVE LOGITS

ConstraintMaker

0.79

ReusableCell

0.79

GEBURTSDATUM

0.78

tagHelperRunner

0.78

mybatisplus

0.77

 '\\;'

0.76

 صوتيه

0.75

writeFieldEnd

0.75

NewUrlParser

0.73

 protoimpl

0.73

Activations Density 1.698%

words and phrases commonly used in business or formal reporting contexts.

comma

No Comments

No Known Activations