INDEX

Explanations

dialogue between two people

oai_token-act-pair · gemini-2.0-flash

I or you

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

tituzione

-0.49

redhat

-0.48

uff

-0.44

histor

-0.43

 affari

-0.42

am

-0.42

 hybrid

-0.42

HEET

-0.42

 delito

-0.40

 podamos

-0.40

POSITIVE LOGITS

ArrowToggle

0.94

 חיצוניים

0.87

aarrggbb

0.79

scrapy

0.78

AxisAlignment

0.75

featureID

0.74

 ProtoMessage

0.73

 <=",

0.73

InjectAttribute

0.72

Geplaatst

0.71

Activations Density 0.495%

dialogue between two people

I or you

No Comments

No Known Activations