INDEX

Explanations

proper nouns, especially names of media like films, episodes, and series

oai_token-act-pair · gemini-2.0-flash

Movie/exhibit names and code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

号

-0.47

 việc

-0.46

 незавершена

-0.45

 везе

-0.44

並

-0.44

 vinaigre

-0.44

omal

-0.42

 laude

-0.41

orians

-0.41

 gili

-0.41

POSITIVE LOGITS

 GenerationType

1.05

 utafitiHapana

1.01

 ModelExpression

0.74

TemporalType

0.71

webElementXpaths

0.71

tagHelperRunner

0.70

Välislingid

0.70

 Winaray

0.66

 estekak

0.65

 cherchés

0.65

Activations Density 2.277%

proper nouns, especially names of media like films, episodes, and series

Movie/exhibit names and code

No Comments

No Known Activations