INDEX

Explanations

words or phrases associated with academic papers, military rankings, sporting events and other scored or ranked activities.

oai_token-act-pair · gemini-2.0-flash

Adult

np_token-act-pair-logits · gemini-2.0-flash

Lists, maps, schedules

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

__(/*!

-0.86

 Normdatei

-0.67

WriteBarrier

-0.65

fjspx

-0.62

 AssemblyVersion

-0.60

KommentareTeilen

-0.59

Portail

-0.59

 للمعارف

-0.59

 iNdEx

-0.58

/******/

-0.56

POSITIVE LOGITS

 Adult

0.52

 adult

0.51

Adult

0.48

 undercover

0.47

WebControls

0.46

tempted

0.46

 incest

0.45

 ujednoznacz

0.44

adult

0.44

toplankton

0.43

Activations Density 1.204%

words or phrases associated with academic papers, military rankings, sporting events and other scored or ranked activities.

Adult

Lists, maps, schedules

No Comments

No Known Activations