INDEX

Explanations

sentences describing legal, political, or social events involving a named group of people

oai_token-act-pair · gemini-2.0-flash

Following events

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

 kasarigan

-0.65

تقاوى

-0.65

QMetaType

-0.62

archiviato

-0.60

 Мексичка

-0.59

Хьажоргаш

-0.55

どく

-0.54

govina

-0.54

ništ

-0.54

DTD

-0.54

POSITIVE LOGITS

 numerous

0.64

]--;

0.62

0.61

 threats

0.55

an

0.55

 multiple

0.54

 rumors

0.52

the

0.52

 widespread

0.52

ⓧ

0.50

Activations Density 3.752%

sentences describing legal, political, or social events involving a named group of people

Following events

No Comments

No Known Activations