INDEX

Explanations

URLs to github.com.

oai_token-act-pair · gemini-2.0-flash

/

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

-0.48

hwar

-0.48

 defaultstate

-0.46

noid

-0.46

,'\

-0.45

tagHelper

-0.45

fileID

-0.44

Inflater

-0.43

othea

-0.42

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.76

ыгана

0.72

kepada

0.68

 متعلقه

0.66

 Италијани

0.66

 čierna

0.63

 AssemblyTitle

0.63

RuleContext

0.62

 ddelweddau

0.62

 صوتيه

0.61

Activations Density 0.294%

URLs to github.com.

/

No Comments

No Known Activations

URLs to github.com.

/

No Comments

No Known Activations