INDEX

Explanations

possessive nouns and terms for groups of people.

oai_token-act-pair · gemini-2.0-flash

apostrophes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

</thead>

-0.52

ⓘ

-0.50

 prayed

-0.47

 volont

-0.47

 transmiti

-0.45

ദ്

-0.45

 doubted

-0.45

 Critics

-0.45

 unfolding

-0.44

 fawn

-0.44

POSITIVE LOGITS

 HasFactory

0.79

 autorytatywna

0.76

FunctionFlags

0.72

 चीज़ों

0.69

{}/

0.67

webElementXpaths

0.67

AsUp

0.65

хьтан

0.65

Autoritní

0.65

BoxShadow

0.65

Activations Density 2.601%

possessive nouns and terms for groups of people.

apostrophes

No Comments

No Known Activations