INDEX

Explanations

things that can be 'unlocked'/improved in the game.

oai_token-act-pair · gemini-2.0-flash

terms related to gaming customization or features

np_token-act-pair-logits · gpt-4o-mini

Kits

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

neous

-0.46

 stål

-0.42

 généraux

-0.41

pij

-0.41

 ministres

-0.40

 particulières

-0.40

 Port

-0.39

Pol

-0.38

forChild

-0.38

Port

-0.38

POSITIVE LOGITS

 kits

0.89

kit

0.80

parsedMessage

0.78

IsMutable

0.77

Kit

0.76

enumi

0.75

 Kits

0.75

KIT

0.74

Tikang

0.74

ScopeManager

0.73

Activations Density 1.217%

things that can be 'unlocked'/improved in the game.

terms related to gaming customization or features

Kits

No Comments

No Known Activations