INDEX

Explanations

sentences where authors describe their work and beliefs, especially using verbs and prepositions.

oai_token-act-pair · gemini-2.0-flash

the

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ScopeManager

-0.81

GEBURTSDATUM

-0.79

Personensuche

-0.77

NewUrlParser

-0.76

تقاوى

-0.76

iastes

-0.74

rungsseite

-0.73

cshtml

-0.73

 wireType

-0.71

OGND

-0.71

POSITIVE LOGITS

the

1.40

 την

0.50

 τις

0.49

the

0.49

 τη

0.47

 τα

0.44

uração

0.43

 nødven

0.41

 את

0.41

 godt

0.40

Activations Density 2.507%

sentences where authors describe their work and beliefs, especially using verbs and prepositions.

the

No Comments

No Known Activations