INDEX

Explanations

references to video games, especially older ones, and text related to downloading them.

oai_token-act-pair · gemini-2.0-flash

games and gaming

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

SharedCtor

-0.79

adaptiveStyles

-0.62

 ivelany

-0.60

 Roskov

-0.60

enterOuterAlt

-0.57

Enllaces

-0.56

 Preferencias

-0.56

ViewFeatures

-0.54

rank

-0.53

addCriterion

-0.53

POSITIVE LOGITS

DockStyle

0.47

 Ante

0.47

Kane

0.46

 GenerationType

0.45

 Fores

0.45

andis

0.44

Ante

0.43

 Rame

0.43

Amer

0.42

 crat

0.42

Activations Density 0.429%

references to video games, especially older ones, and text related to downloading them.

games and gaming

No Comments

No Known Activations