INDEX

Explanations

mentions of years, especially years BC

oai_token-act-pair · gemini-2.0-flash

Dates and centuries

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

 виправивши

-0.79

parsedMessage

-0.74

rungsseite

-0.73

 مرئيه

-0.67

 autorytatywna

-0.64

ItemBackground

-0.63

 ChromeDriver

-0.61

 Drapeau

-0.60

AndroidJUnit

-0.60

 ennemis

-0.60

POSITIVE LOGITS

ad

0.51

AD

0.48

manuelle

0.46

šė

0.46

 avance

0.45

ady

0.45

まま

0.44

 advance

0.43

 live

0.43

 hundred

0.43

Activations Density 0.962%

mentions of years, especially years BC

Dates and centuries

No Comments

No Known Activations