INDEX

Explanations

code related to website design and job postings

oai_token-act-pair · gemini-2.0-flash

Code component styling

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 Мексичка

-0.84

 esternos

-0.78

AntiForgeryToken

-0.77

 nahilalakip

-0.73

 EconPapers

-0.73

LookAnd

-0.72

 >=",

-0.72

SourceChecksum

-0.66

 pinulongan

-0.65

HandlerContext

-0.65

POSITIVE LOGITS

 grid

0.56

My

0.47

 Grid

0.46

My

0.45

Grid

0.45

 player

0.44

grid

0.44

 marca

0.42

 kuiten

0.41

Now

0.40

Activations Density 3.395%

code related to website design and job postings

Code component styling

No Comments

No Known Activations