INDEX

Explanations

code snippets and associated keywords like `handler`, `element`, `attribute`, `function`, `string`, `status`

oai_token-act-pair · gemini-2.0-flash

code, programming

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

 дописавши

-0.58

 pañ

-0.55

delige

-0.53

 eccl

-0.47

overhead

-0.47

 démocr

-0.47

 financières

-0.47

 culturelles

-0.45

 fondament

-0.45

 traités

-0.44

POSITIVE LOGITS

 program

0.80

0.79

 Program

0.72

 PROGRAM

0.69

Program

0.68

 readFile

0.66

program

0.65

MockMvc

0.63

PROGRAM

0.63

 IndexPath

0.62

Activations Density 18.363%

code snippets and associated keywords like `handler`, `element`, `attribute`, `function`, `string`, `status`

code, programming

No Comments

No Known Activations