INDEX

Explanations

mentions of powers and skills

oai_token-act-pair · gemini-2.0-flash

skills and abilities

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

nanoTime

-0.66

InstanceState

-0.63

EndGlobalSection

-0.62

 GeoNames

-0.59

RegistryLite

-0.58

]")]

-0.57

 intptr

-0.57

obenz

-0.56

erals

-0.56

SourceChecksum

-0.55

POSITIVE LOGITS

 abilities

0.96

 skills

0.96

 skill

0.88

skills

0.79

 Skills

0.78

 ability

0.77

 Abilities

0.74

 Skill

0.71

Skills

0.69

Skill

0.67

Activations Density 1.108%

mentions of powers and skills

skills and abilities

No Comments

No Known Activations