INDEX

Explanations

code snippets, especially C# and Java, involving caching, XML, and string manipulation

oai_token-act-pair · gemini-2.0-flash

code and errors

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

PreferredItem

-0.55

 Eras

-0.54

 NSCoder

-0.52

 виправивши

-0.50

vels

-0.50

eras

-0.49

internalType

-0.49

 Majest

-0.49

出版年

-0.49

 boroughs

-0.47

POSITIVE LOGITS

saraba

0.57

 &___

0.56

 secondaires

0.54

 efficaces

0.54

ParallelGroup

0.53

//

0.52

 természetes

0.51

℗

0.51

 naturelles

0.49

#{

0.49

Activations Density 0.891%

code snippets, especially C# and Java, involving caching, XML, and string manipulation

code and errors

No Comments

No Known Activations