INDEX

Explanations

words related to health, technology, finance, abuse, and cybersecurity

oai_token-act-pair · gemini-2.0-flash

Business sectors/industries

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

uxxxx

-0.65

Geplaatst

-0.57

دانشنامهٔ

-0.53

TestFixture

-0.52

IVEREF

-0.50

orique

-0.49

riwal

-0.47

})));

-0.47

هات

-0.46

 kaarangay

-0.46

POSITIVE LOGITS

 world

0.60

TypedDataSet

0.59

SpringRunner

0.52

mybatisplus

0.51

FTFY

0.50

Примітки

0.50

 poffe

0.50

world

0.49

 hashCode

0.48

DrawerToggle

0.48

Activations Density 7.763%

words related to health, technology, finance, abuse, and cybersecurity

Business sectors/industries

No Comments

No Known Activations