INDEX

Explanations

the keyword "int" in code snippets, with some activation for other elements of Android XML code

oai_token-act-pair · gemini-2.0-flash

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 dikem

-0.50

 protoimpl

-0.49

mete

-0.48

osgi

-0.44

CAP

-0.44

sizeCache

-0.43

 kív

-0.43

cap

-0.42

hyperref

-0.42

DataInputStream

-0.40

POSITIVE LOGITS

 saites

0.73

Rujuakan

0.73

AsUp

0.66

weder

0.65

tdessen

0.60

etCode

0.59

íncia

0.59

intellij

0.58

 cherchés

0.58

brainly

0.58

Activations Density 0.266%

the keyword "int" in code snippets, with some activation for other elements of Android XML code

code

No Comments

No Known Activations