INDEX

Explanations

mathematical or currency expressions

oai_token-act-pair · gemini-2.0-flash

technical/scientific texts

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

 near

-0.67

eseorang

-0.64

jecha

-0.63

脚注の使い方

-0.62

VIAF

-0.60

 człowie

-0.58

 morire

-0.57

bibinfo

-0.56

Near

-0.56

Instrucciones

-0.54

POSITIVE LOGITS

XmlEnum

0.51

styleType

0.45

̍t

0.45

 Kame

0.45

LayoutPanel

0.44

 aDecoder

0.44

 Kiel

0.44

 Kenne

0.43

Diwedd

0.43

Tembelea

0.43

Activations Density 3.372%

mathematical or currency expressions

technical/scientific texts

No Comments

No Known Activations