INDEX

Explanations

words and descriptions pertaining to medical observations about an injury, its treatment, and healing, plus mental health conditions and therapies

oai_token-act-pair · gemini-2.0-flash

healing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 healing

-1.95

 therapeutic

-1.91

Healing

-1.76

 Healing

-1.76

healing

-1.72

 heal

-1.67

 healed

-1.66

 therapy

-1.63

 Therapeutic

-1.59

 heals

-1.58

POSITIVE LOGITS

 Normdatei

0.59

ParallelGroup

0.58

enumi

0.56

 للاسماء

0.56

complexContent

0.55

">—

0.55

GeneratedMessage

0.53

IsContent

0.53

OGND

0.52

:✨

0.52

Activations Density 2.762%

words and descriptions pertaining to medical observations about an injury, its treatment, and healing, plus mental health conditions and therapies

healing

No Comments

No Known Activations