INDEX

Explanations

programming code and database table descriptions

oai_token-act-pair · gemini-2.0-flash

SQL database tables

np_token-act-pair-logits · gemini-2.0-flash

programming symbols

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

-0.73

UserScript

-0.69

RuleContext

-0.68

ⓧ

-0.68

клопе

-0.66

 تضيفلها

-0.66

Geplaatst

-0.57

ArrowToggle

-0.56

UnitTesting

-0.56

 NDEBUG

-0.55

POSITIVE LOGITS

 studio

0.51

]<<

0.48

electric

0.48

 sash

0.48

athlon

0.47

 сту

0.47

linde

0.47

Vea

0.47

 Chambre

0.46

 shop

0.46

Activations Density 3.364%

programming code and database table descriptions

SQL database tables

programming symbols

No Comments

No Known Activations