INDEX

Explanations

mentions of daily life and work

oai_token-act-pair · gemini-2.0-flash

daily

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

AndEndTag

-0.87

 AssemblyTitle

-0.77

expandindo

-0.75

 saites

-0.75

曖昧さ回避

-0.74

 Italijanski

-0.73

Datuak

-0.71

 noDo

-0.69

hoeddwyd

-0.68

 Chwiliwch

-0.67

POSITIVE LOGITS

CopyWith

0.46

 buzz

0.45

eng

0.45

 keren

0.44

镜像

0.42

 Handlungen

0.42

ogr

0.41

 насеље

0.41

льники

0.41

obis

0.41

Activations Density 1.082%

mentions of daily life and work

daily

No Comments

No Known Activations