INDEX

Explanations

terms related to software development and running programs

oai_token-act-pair · gemini-2.0-flash

Code and file paths

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

外部リンク

-0.56

 cannibal

-0.53

Dade

-0.50

Handlung

-0.47

pela

-0.46

 menudo

-0.45

 ModelExpression

-0.44

 campaigned

-0.44

tisol

-0.43

 intitulé

-0.43

POSITIVE LOGITS

 autorytatywna

0.84

 unknownFields

0.70

 ComVisible

0.67

uxxxx

0.65

^(@)

0.63

出版年

0.62

NameInMap

0.60

AddTagHelper

0.59

InteropServices

0.58

intios

0.57

Activations Density 8.100%

terms related to software development and running programs

Code and file paths

No Comments

No Known Activations