INDEX

Explanations

words related to historical significance and preservation

oai_token-act-pair · gemini-2.0-flash

historic listings

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 betweenstory

-0.57

LookAnd

-0.57

ThroughAttribute

-0.55

 asexual

-0.54

 utafiti

-0.52

 allá

-0.51

ViewFeatures

-0.51

 Plastic

-0.51

Geplaatst

-0.50

 NUKAT

-0.50

POSITIVE LOGITS

 Listed

0.67

 listed

0.63

 existing

0.63

 historic

0.60

existing

0.59

 bestaande

0.59

disposing

0.58

 viewDidLoad

0.56

</thead>

0.56

 listings

0.54

Activations Density 2.083%

words related to historical significance and preservation

historic listings

No Comments

No Known Activations