INDEX

Explanations

mentions of people collaborating or working together on projects

oai_token-act-pair · gemini-2.0-flash

work

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

:✨

-0.65

Datuak

-0.61

ValueStyle

-0.59

windowFixed

-0.57

tonode

-0.57

Referències

-0.57

Personendaten

-0.57

Tembelea

-0.55

ruled

-0.54

 "'",

-0.54

POSITIVE LOGITS

 with

0.59

 resourceCulture

0.59

 Estatal

0.57

culares

0.49

ellido

0.49

กับ

0.49

сота

0.48

 MenuView

0.48

τως

0.48

 mắn

0.47

Activations Density 0.489%

mentions of people collaborating or working together on projects

work

No Comments

No Known Activations