INDEX

Explanations

lines of asterisks and/or equals signs

oai_token-act-pair · gemini-2.0-flash

code comments and separators

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 JsonResult

-0.48

 IActionResult

-0.46

Ful

-0.46

 edili

-0.45

 dist

-0.44

ForRow

-0.43

usercontent

-0.43

dist

-0.42

(()

-0.42

kwds

-0.42

POSITIVE LOGITS

 BorderRadius

0.68

<bos>

0.67

 متعلقه

0.66

 disambiguazione

0.61

出版年

0.60

brainly

0.60

########.

0.59

+:+

0.58

\{\\

0.58

ddots

0.57

Activations Density 1.048%

lines of asterisks and/or equals signs

code comments and separators

No Comments

No Known Activations