INDEX

Explanations

phrases emphasizing a specific point or connection

oai_token-act-pair · gemini-2.0-flash

positive emotions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ISNI

-0.61

ыгана

-0.60

apimachinery

-0.59

eniendo

-0.54

parsedMessage

-0.53

marshaller

-0.52

OrCreate

-0.52

 newBuilder

-0.50

 vorbehalten

-0.48

VersionUID

-0.48

POSITIVE LOGITS

 excited

0.73

 determined

0.71

IntoConstraints

0.71

 willing

0.70

 enthusiastic

0.68

 passionate

0.67

 embarrassed

0.66

 angry

0.65

 qualified

0.65

 satisfied

0.64

Activations Density 4.971%

phrases emphasizing a specific point or connection

positive emotions

No Comments

No Known Activations