INDEX

Explanations

place names relating to France and cities, specifically "Saint-...", and "ville" or "canton."

oai_token-act-pair · gemini-2.0-flash

French place names

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 city

-0.73

 cities

-0.56

WebServlet

-0.53

 City

-0.52

basicConfig

-0.51

city

-0.51

 capital

-0.49

Jeografia

-0.48

 ciudad

-0.48

 città

-0.47

POSITIVE LOGITS

 Keepers

0.65

FontOfSize

0.62

 IBOutlet

0.57

 tartalomajánló

0.57

essero

0.57

ματα

0.57

zzar

0.56

getChildAt

0.56

 undercut

0.55

othelioma

0.55

Activations Density 0.603%

place names relating to France and cities, specifically "Saint-...", and "ville" or "canton."

French place names

No Comments

No Known Activations