INDEX

Explanations

sections of code with comments defining code blocks, classes, tests, and usage of classes.

oai_token-act-pair · gemini-2.0-flash

code related words

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

ReusableCell

-0.69

 lenker

-0.69

titleMargin

-0.69

Autoritní

-0.67

ChildScrollView

-0.67

IVEREF

-0.67

transQ

-0.66

 RequestMethod

-0.65

 Audiodateien

-0.65

 ExecuteAsync

-0.65

POSITIVE LOGITS

class

0.60

Class

0.57

use

0.56

TabIndex

0.56

Geplaatst

0.52

add

0.46

Hab

0.43

Use

0.43

used

0.42

 class

0.42

Activations Density 0.369%

sections of code with comments defining code blocks, classes, tests, and usage of classes.

code related words

No Comments

No Known Activations