INDEX

Explanations

language used in patents and legal documents, particularly regarding inventions, embodiments, and manufacturing processes

oai_token-act-pair · gemini-2.0-flash

including

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

#+#

-0.60

 unknownFields

-0.59

knowing

-0.58

SourceChecksum

-0.57

 knowing

-0.56

 Мексичка

-0.55

 remaining

-0.53

HasAnnotation

-0.52

########.

-0.52

QMetaType

-0.51

POSITIVE LOGITS

 including

1.44

 Including

1.21

Including

1.15

including

1.15

 INCLUDING

1.03

 incluyendo

1.02

 ranging

1.01

 incluindo

0.99

 waaronder

0.89

 involving

0.89

Activations Density 18.481%

language used in patents and legal documents, particularly regarding inventions, embodiments, and manufacturing processes

including

No Comments

No Known Activations