INDEX

Explanations

Objective-C code

oai_token-act-pair · gemini-2.0-flash

Objective-C code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

はじめに

-0.69

\{\\

-0.63

 ***!

-0.62

:✨

-0.62

ScopeManager

-0.55

ніципа

-0.52

tanleria

-0.52

 Drapeau

-0.51

tagHelperRunner

-0.51

\}\\

-0.50

POSITIVE LOGITS

RUnlock

0.54

MockMvc

0.50

रोध

0.49

aerop

0.49

 Профиль

0.48

 useNavigate

0.48

IntoConstraints

0.47

su

0.47

rainian

0.47

decke

0.46

Activations Density 1.702%

Objective-C code

Objective-C code

No Comments

No Known Activations