INDEX

Explanations

terms describing families, membership and connections

oai_token-act-pair · gemini-2.0-flash

members and membership

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 member

-3.33

 members

-3.13

 Member

-3.09

 Members

-3.08

Member

-3.00

member

-3.00

Members

-2.97

 MEMBER

-2.95

members

-2.88

 MEMBERS

-2.78

POSITIVE LOGITS

 الرياضيه

0.40

ांक

0.36

roits

0.34

mişti

0.33

 isolato

0.33

estacks

0.33

ekan

0.33

 Projektu

0.33

mette

0.33

 Verfügung

0.32

Activations Density 1.345%

terms describing families, membership and connections

members and membership

No Comments

No Known Activations