INDEX

Explanations

code snippets that define sets of properties and methods especially regarding messages and data storage

oai_token-act-pair · gemini-2.0-flash

Non-English words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

getLatitude

-0.46

iotensin

-0.46

 pand

-0.45

-0.40

 Vign

-0.40

 moment

-0.40

 cortesía

-0.38

zur

-0.38

rifts

-0.37

POSITIVE LOGITS

 незавершена

0.91

 فريبيس

0.91

tagHelperRunner

0.83

 disambiguazione

0.83

 linkovi

0.81

 ThemeData

0.79

 مرئيه

0.79

Datuak

0.79

 ExecuteAsync

0.79

 Мексичка

0.77

Activations Density 0.119%

code snippets that define sets of properties and methods especially regarding messages and data storage

Non-English words

No Comments

No Known Activations