INDEX

Explanations

statistical results and achievements within the context of sports, specifically athletic championships, medals, and races

oai_token-act-pair · gemini-2.0-flash

sports and awards

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 qualified

-1.00

 qualification

-0.91

 Qualified

-0.89

 QUAL

-0.84

 qualify

-0.84

 qualifier

-0.84

 qualifying

-0.84

qual

-0.82

qualified

-0.82

 nakalista

-0.81

POSITIVE LOGITS

ordinating

0.43

Général

0.43

Uninitialized

0.42

 carnival

0.42

multer

0.41

Andrés

0.41

صاد

0.40

 Regu

0.39

ρώ

0.39

antos

0.39

Activations Density 2.368%

statistical results and achievements within the context of sports, specifically athletic championships, medals, and races

sports and awards

No Comments

No Known Activations