INDEX

Explanations

references to people who have some kind of fame or status

oai_token-act-pair · gemini-2.0-flash

varied topics

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

 Anſ

-0.83

 Monfieur

-0.75

 ſtate

-0.72

Eſ

-0.72

 Diſ

-0.71

 pleaſure

-0.71

 Houſe

-0.68

 ſta

-0.68

 juſ

-0.67

 ſche

-0.66

POSITIVE LOGITS

 utafitiHapana

0.67

ChildScrollView

0.58

 Audiodateien

0.58

Personensuche

0.54

peq

0.54

IntoConstraints

0.53

0.52

antMatchers

0.52

styleType

0.52

MessageOf

0.52

Activations Density 3.495%

references to people who have some kind of fame or status

varied topics

No Comments

No Known Activations