INDEX

Explanations

variables, operators, and notation commonly used in math and statistics, especially those that are enclosed in '$' symbols and used in formulas

oai_token-act-pair · gemini-2.0-flash

Mathematical notation

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

 betweenstory

-0.58

 forty

-0.43

myn

-0.42

TagHelper

-0.41

рация

-0.41

__':

-0.41

ÄT

-0.40

 nine

-0.39

 seven

-0.39

 eight

-0.39

POSITIVE LOGITS

Дереккөздер

0.69

таратура

0.67

Jereo

0.63

0.59

 AspNetCore

0.58

 оригіналу

0.57

XmlAccessType

0.57

 MaterialApp

0.56

 financieras

0.55

oneta

0.54

Activations Density 1.761%

variables, operators, and notation commonly used in math and statistics, especially those that are enclosed in '$' symbols and used in formulas

Mathematical notation

No Comments

No Known Activations