INDEX

Explanations

proper nouns

oai_token-act-pair · gemini-2.0-flash

Names and locations

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

-0.51

UG

-0.48

IF

-0.47

PD

-0.47

-0.46

AB

-0.46

CH

-0.46

AV

-0.45

POSITIVE LOGITS

出版年

0.96

ViewFeatures

0.87

ValueStyle

0.85

 resourceCulture

0.80

Personendaten

0.79



0.75

脚注の使い方

0.73

 surla

0.71

extAlignment

0.70

 дописавши

0.69

Activations Density 3.133%

proper nouns

Names and locations

No Comments

No Known Activations