INDEX

Explanations

scientific and technical terms from studies and experiments

oai_token-act-pair · gemini-2.0-flash

terase

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

GEBURTSDATUM

-0.95

Tikang

-0.93

TestingModule

-0.93

Искәрмәләр

-0.91

DOCTYPE

-0.82

DIE

-0.81

tableFuture

-0.77

 AssemblyCompany

-0.77

 saites

-0.77

Portail

-0.77

POSITIVE LOGITS

...

0.71

нг

0.62

Matth

0.59

 Stras

0.56

aw

0.56

ly

0.56

ModelAdmin

0.55

біль

0.55

ظ

0.54

co

0.54

Activations Density 7.657%

scientific and technical terms from studies and experiments

terase

No Comments

No Known Activations