INDEX

Explanations

words related to computer or mechanical processes

oai_token-act-pair · gemini-2.0-flash

technical processes/data

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

<bos>

-1.67

 pinulongan

-0.45

 pushed

-0.42

getSeconds

-0.42

engertian

-0.42

 للمعارف

-0.41

 المعيارى

-0.40

-0.39

 willst

-0.39

 center

-0.38

POSITIVE LOGITS

 Roskov

0.73

 jPanel

0.70

 jScrollPane

0.67

ruptedException

0.63

 Wayback

0.63

ReusableCell

0.61

ẠI

0.60

WebElementEntity

0.58

pidou

0.57

uccino

0.57

Activations Density 15.378%

words related to computer or mechanical processes

technical processes/data

No Comments

No Known Activations