INDEX

Explanations

medical terms relating to diseases and body systems

oai_token-act-pair · gemini-2.0-flash

medical conditions/systems

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

endaftar

-0.63

contentLoaded

-0.48

 entrambi

-0.46

 >=",

-0.46

 lists

-0.45

 qualitatively

-0.45

 "..\..\

-0.44

UnifiedTopology

-0.44

jgl

-0.43

 OMITBAD

-0.43

POSITIVE LOGITS

 system

0.63

 Réponses

0.62

Personendaten

0.60

 NSCoder

0.58

 يتيمه

0.57

 System

0.56

 systeem

0.55

CloseOperation

0.54

uleiro

0.54



0.53

Activations Density 1.505%

medical terms relating to diseases and body systems

medical conditions/systems

No Comments

No Known Activations