INDEX

Explanations

markers of personal opinion or reflection, often using intensifiers

oai_token-act-pair · gemini-2.0-flash

interest

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

 يتيمه

-0.85

Hentet

-0.77

RenderAtEndOf

-0.76

 صوتيه

-0.73

 Normdatei

-0.71

 חיצוניים

-0.71

 otomatig

-0.69

 ujednoznacz

-0.68

 }}"></

-0.68

TargetException

-0.67

POSITIVE LOGITS

 interest

0.72

 interested

0.64

 interests

0.59

interest

0.59

 Interest

0.51

Interest

0.51

interested

0.50

 zainteres

0.50

 Interested

0.50

INTEREST

0.48

Activations Density 1.873%

markers of personal opinion or reflection, often using intensifiers

interest

No Comments

No Known Activations