INDEX

Explanations

positive adjectives

oai_token-act-pair · gemini-2.0-flash

perfect, ideal

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

SourceChecksum

-0.75

ValueStyle

-0.75

IVEREF

-0.71

 ویکی‌پدیا

-0.66

sizeCache

-0.66

onViewCreated

-0.65

RectangleBorder

-0.64

ANTLR

-0.63

ThroughAttribute

-0.62

UnsafeEnabled

-0.62

POSITIVE LOGITS

 perfect

3.00

perfect

2.81

 ideal

2.66

Perfect

2.53

 Perfect

2.47

ideal

2.44

Ideal

2.28

 Ideal

2.23

 PERFECT

2.17

 perfecto

2.14

Activations Density 1.480%

positive adjectives

perfect, ideal

No Comments

No Known Activations