INDEX

Explanations

Latex math expressions with exponents

oai_token-act-pair · gemini-2.0-flash

scientific and code snippets

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

aarrggbb

-0.81

Tembelea

-0.72

Története

-0.71

ContentLoaded

-0.71

 intptr

-0.68

mappedBy

-0.66

 kasarigan

-0.66

énario

-0.65

.*")]

-0.61

net

-0.59

POSITIVE LOGITS

<bos>

0.58

OrderService

0.48

 arreglo

0.48

ApplicationTests

0.47

عية

0.47

 treno

0.44

澳门

0.44

 sonno

0.44

RetentionPolicy

0.44

true

0.43

Activations Density 2.195%

Latex math expressions with exponents

scientific and code snippets

No Comments

No Known Activations