INDEX

Explanations

words that modify or add emphasis to an adjective

oai_token-act-pair · gemini-2.0-flash

Something is sufficient

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 enough

-2.58

enough

-2.30

 Enough

-2.19

Enough

-2.03

 ENOUGH

-1.99

 genug

-1.72

 sufficient

-1.72

 suficiente

-1.71

 genoeg

-1.70

 Sufficient

-1.63

POSITIVE LOGITS

NoSuchAlgorithm

0.55

getBean

0.40

рядок

0.40

RestTemplate

0.40

bigniew

0.39

 lavage

0.39

FXMLLoader

0.39

 Vicar

0.38

LayoutParams

0.38

illoin

0.38

Activations Density 2.450%

words that modify or add emphasis to an adjective

Something is sufficient

No Comments

No Known Activations