INDEX

Explanations

mentions of TV series

oai_token-act-pair · gemini-2.0-flash

television series, tv series, series.Final Answer: series

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 series

-0.70

-0.59

Revenir

-0.59

 veritable

-0.57

 Series

-0.57

multirow

-0.57

 industry

-0.56

new

-0.54

 Others

-0.54

 Moving

-0.54

POSITIVE LOGITS

<bos>

1.08

Personensuche

0.83

@"/

0.82

 AssemblyTitle

0.82

GEBURTSDATUM

0.81

 ProtoMessage

0.79

 refusé

0.78

 pitié

0.76

Obrázky

0.75

 feroit

0.73

Activations Density 0.671%

mentions of TV series

television series, tv series, series.Final Answer: series

No Comments

No Known Activations