INDEX

Explanations

Java annotations and imports for persistence and related frameworks

oai_token-act-pair · gemini-2.0-flash

@ and

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

parsedMessage

-1.03

AsUp

-0.97

 itſelf

-0.96

AnchorStyles

-0.87

 Drapeau

-0.83

 myſelf

-0.82

 المعيارى

-0.82

ViewFeatures

-0.82

 Autorizaciones

-0.81

 >=",

-0.81

POSITIVE LOGITS

BeforeClass

0.50

↵

0.45

var

0.43

nac

0.41

aj

0.39

0.38

↵↵

0.38

//

0.36

SuppressWarnings

0.36

Activations Density 4.703%

Java annotations and imports for persistence and related frameworks

@ and

No Comments

No Known Activations