INDEX

Explanations

words related to legal proceedings and judgements, especially negligence

oai_token-act-pair · gemini-2.0-flash

negligence

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

 ब्रेकडाउन

-0.68

 OMITBAD

-0.62

 Normdatei

-0.58

 pié

-0.54

 >=",

-0.54

 Klon

-0.52

httphttps

-0.51

withIdentifier

-0.50

 royals

-0.50

 Swedes

-0.49

POSITIVE LOGITS

 المعيارى

0.67

kloped

0.63

 fallu

0.60

 Réponses

0.57

)‏

0.56

dä

0.56

ttino

0.55

出版年

0.55

stående

0.52

osoba

0.52

Activations Density 2.144%

words related to legal proceedings and judgements, especially negligence

negligence

No Comments

No Known Activations