INDEX

Explanations

terminology related to medical treatment or conditions

oai_token-act-pair · gemini-2.0-flash

mentions of medication and treatment

np_token-act-pair-logits · gpt-4o-mini

medicine/drugs

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

fromnode

-0.68

StoryboardSegue

-0.59

Espèce

-0.59

󠁴

-0.58

 MaterialApp

-0.58

 sauvages

-0.57

Abitanti

-0.56

 utafitiHapana

-0.56

 صوتيه

-0.56

rungsseite

-0.56

POSITIVE LOGITS

Ground

0.59

 ground

0.58

 Ground

0.57

dopodob

0.53

met

0.53

 round

0.52

Met

0.51

ground

0.50

Pla

0.50

Activations Density 3.648%

terminology related to medical treatment or conditions

mentions of medication and treatment

medicine/drugs

No Comments

No Known Activations