INDEX

Explanations

mathematical equations and formulas

oai_token-act-pair · gemini-2.0-flash

math/code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

MigrationBuilder

-0.66

 ExecuteAsync

-0.61

########.

-0.59

sidemargin

-0.59

 nonatomic

-0.59

__":

-0.57

 himo

-0.56

</blockquote>

-0.56

 ویکی‌پدیا

-0.55

";

-0.54

POSITIVE LOGITS

1.01

TableAdapter

0.66

♥♥

0.62

 ioutil

0.59

()"

0.55

 Beller

0.54

SharedCtor

0.52

vably

0.50

 Перейти

0.50

0.48

Activations Density 2.842%

mathematical equations and formulas

math/code

No Comments

No Known Activations