INDEX

Explanations

code related to video encoding related constants and struct definitions

oai_token-act-pair · gemini-2.0-flash

F

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

hdashline

-0.52

ukone

-0.51

 Winkel

-0.51

łka

-0.50

 BROTHERS

-0.50

Carriera

-0.47

DoubleQuotes

-0.46

TestingModule

-0.46

InputTagHelper

-0.46

execSQL

-0.45

POSITIVE LOGITS

 linkovi

0.65

 AssemblyCulture

0.60

Viitteet

0.58

Personendaten

0.57

 Lush

0.57

 judiciales

0.55

abetes

0.54

 hoort

0.53

 Мексичка

0.52

✨:

0.52

Activations Density 4.006%

code related to video encoding related constants and struct definitions

F

No Comments

No Known Activations