INDEX

Explanations

mentions of awards, ceremonies, and contests

oai_token-act-pair · gemini-2.0-flash

awards

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 NSCoder

-0.95

 propOrder

-0.78

 Baillargeon

-0.73

Datuak

-0.71

 tartalomajánló

-0.70

Geplaatst

-0.68

parsedMessage

-0.66

VIAF

-0.66

ArrowToggle

-0.66

 AssemblyCulture

-0.65

POSITIVE LOGITS

 awards

0.85

 Awards

0.74

Awards

0.68

 Award

0.65

 award

0.65

 honored

0.65

 honors

0.64

 honor

0.63

 AWARD

0.57

Premios

0.57

Activations Density 0.337%

mentions of awards, ceremonies, and contests

awards

No Comments

No Known Activations