INDEX

Explanations

french words and phrases, especially those used in online conversation

oai_token-act-pair · gemini-2.0-flash

French internet chat

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

исленность

-0.87

 виправивши

-0.78

 Мексичка

-0.75

AddTagHelper

-0.72

 שוליים

-0.70

vature

-0.64

zielle

-0.63

 ujednoznacz

-0.63

PreferredItem

-0.61

 NSCoder

-0.61

POSITIVE LOGITS

de

0.61

del

0.50

joined

0.43

 convertView

0.43



0.42

 Comment

0.42

Join

0.41

ly

0.41

ent

0.41

pic

0.40

Activations Density 0.817%

french words and phrases, especially those used in online conversation

French internet chat

No Comments

No Known Activations