INDEX

Explanations

phrases expressing difficulty or ability

oai_token-act-pair · gemini-2.0-flash

difficulty

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

RegistryLite

-0.62

gnore

-0.56

primaryStage

-0.50

 Reconnaissance

-0.50

 Concentration

-0.49

rak

-0.49

sief

-0.48

 savez

-0.48

 Himalayan

-0.47

 Pigment

-0.47

POSITIVE LOGITS

 difficult

1.03

 hard

0.97

difficult

0.90

 hardest

0.83

 harder

0.82

Difficult

0.81

 Difficult

0.81

hard

0.80

Hard

0.79

 moeilijk

0.76

Activations Density 0.406%

phrases expressing difficulty or ability

difficulty

No Comments

No Known Activations