INDEX

Explanations

words, phrases, and names associated with companies or organizations

oai_token-act-pair · gemini-2.0-flash

Job-related website context

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

 intitulée

-0.63

 ogóle

-0.60

 vectorielles

-0.56

 közül

-0.55

UpInside

-0.55

 mourir

-0.54

 Rayleigh

-0.54

 pagină

-0.53

niosek

-0.53

 titulada

-0.52

POSITIVE LOGITS

 AssemblyTitle

0.73

DoubleQuotes

0.57

 Tours

0.53

bours

0.52

 Institutes

0.52

 laude

0.48

 Professions

0.48

وصلات

0.47

isers

0.47

ようになります

0.46

Activations Density 12.283%

words, phrases, and names associated with companies or organizations

Job-related website context

No Comments

No Known Activations