INDEX

Explanations

Java or Python code, especially related to web apps and frameworks

oai_token-act-pair · gemini-2.0-flash

springframework

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 kasarigan

-0.59

はじめに

-0.58

AutoScaleMode

-0.57

InteropServices

-0.57

 <<<<<<<<<<<<<<

-0.56

 kaynağından

-0.52

XMLSchema

-0.51

 onCreateView

-0.51

BackPressed

-0.50

 CreateTagHelper

-0.49

POSITIVE LOGITS

 ویکی‌پدیا

0.50

 sanitaires

0.47

 Tasche

0.42

 étan

0.40

 Relaciones

0.39

ędziesz

0.39

 enfans

0.39

 mérit

0.38

photobucket

0.36

 définiti

0.36

Activations Density 0.206%

Java or Python code, especially related to web apps and frameworks

springframework

No Known Activations