INDEX

Explanations

the names of places, rivers, and family members, along with surrounding context words

oai_token-act-pair · gemini-2.0-flash

Locations and legal

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Jeografia

-0.79

AxisAlignment

-0.75

المناصب

-0.72

LookAnd

-0.66

lgari

-0.56

ArrowToggle

-0.54

ilever

-0.54

 Stations

-0.53

Geplaatst

-0.52

AccessorTable

-0.52

POSITIVE LOGITS

coe

0.46

getWriter

0.44

чественной

0.43

attare

0.43

 merito

0.43

Arm

0.43

 Normdatei

0.42

ETTA

0.41

TAWA

0.41

 RoutedEventArgs

0.41

Activations Density 0.865%

the names of places, rivers, and family members, along with surrounding context words

Locations and legal

No Comments

No Known Activations