INDEX

Explanations

words related to interaction between systems or people and the process of doing so

oai_token-act-pair · gemini-2.0-flash

Interact

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 للاسماء

-0.78

PerformLayout

-0.77

 Мексичка

-0.77

>>()

-0.69

DotNetBar

-0.68

DataSetChanged

-0.65

 ddelweddau

-0.65

ffindor

-0.64

Autoritní

-0.64

extAlignment

-0.64

POSITIVE LOGITS

Bios

0.51

gar

0.49

Gel

0.48

gel

0.48

Gel

0.47

odd

0.45

gol

0.45

sten

0.45

":[{

0.45

 Bios

0.44

Activations Density 13.248%

words related to interaction between systems or people and the process of doing so

Interact

No Comments

No Known Activations