INDEX

Explanations

technical documentation and data, including aerodynamic data, wind tunnels, and scientific research

oai_token-act-pair · gemini-2.0-flash

Scale testing

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

 ComVisible

-0.58

 covalent

-0.58

FTFY

-0.58

GEBURTSDATUM

-0.57

 useEffect

-0.56

SystemColors

-0.54

↹

-0.54

Демографія

-0.53

saraba

-0.52

dataclass

-0.51

POSITIVE LOGITS

 test

0.67

 Full

0.65

 full

0.65

 scale

0.62

full

0.60

Full

0.60

 tests

0.59

 pilot

0.59

scale

0.54

 experiments

0.54

Activations Density 1.893%

technical documentation and data, including aerodynamic data, wind tunnels, and scientific research

Scale testing

No Comments

No Known Activations