INDEX

Explanations

words relating to software, the internet, and travel

oai_token-act-pair · gemini-2.0-flash

post

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 post

-1.73

post

-1.50

 Post

-1.45

Post

-1.35

 POST

-1.32

 Posts

-1.22

 posts

-1.21

POST

-1.16

ポスト

-1.05

 getPost

-1.05

POSITIVE LOGITS

propTypes

0.63

клопе

0.63

 betweenstory

0.53

tamment

0.53

ecap

0.53

 esportivo

0.50

 verbally

0.50

 Offisielt

0.48

 reparation

0.48

artifactId

0.48

Activations Density 22.933%

words relating to software, the internet, and travel

post

No Comments

No Known Activations