INDEX

Explanations

html table syntax

oai_token-act-pair · gemini-2.0-flash

HTML table rows

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 فريبيس

-0.57

học

-0.55

 상세

-0.50

 rús

-0.50

('.

-0.46

Fail

-0.46

 pleins

-0.46

 mash

-0.45

 Reservations

-0.45

 Plow

-0.45

POSITIVE LOGITS

/**

0.68

 AssemblyCompany

0.60

+#+#

0.56

قایناق‌لار

0.54

Distribuzione

0.54

Lähteet

0.53

ParallelGroup

0.52

RTDA

0.51

ernalia

0.48

تفصیلات

0.47

Activations Density 2.208%

html table syntax

HTML table rows

No Comments

No Known Activations