INDEX

Explanations

words and symbols frequently used in scientific publications, especially those related to experimental design and data analysis

oai_token-act-pair · gemini-2.0-flash

Parsing and data extraction

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 extraction

-1.86

 extracted

-1.80

 extract

-1.78

 Extract

-1.73

 Extraction

-1.73

 extracting

-1.73

 extracts

-1.65

Extraction

-1.59

 Extracts

-1.59

Extract

-1.56

POSITIVE LOGITS

AntiForgeryToken

0.69

sidemargin

0.57

 Infórmanos

0.49

setVerticalGroup

0.49

pointments

0.48

 colspan

0.48

 territoires

0.48

naphthal

0.47

limia

0.46

ospor

0.46

Activations Density 2.817%

words and symbols frequently used in scientific publications, especially those related to experimental design and data analysis

Parsing and data extraction

No Comments

No Known Activations