INDEX

Explanations

words related to scientific studies of chemical and biological properties, especially those that are beneficial or have potential.

oai_token-act-pair · gemini-2.0-flash

ability

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

เฟ

-0.52

 présidentielle

-0.48

 Plan

-0.48

eraard

-0.46

 Grin

-0.46

enment

-0.46

ochim

-0.46

 espin

-0.44

djangoproject

-0.43

"]}

-0.43

POSITIVE LOGITS

 capacity

1.76

 ability

1.74

 capability

1.72

 abilities

1.71

 capacities

1.62

 capabilities

1.56

capacity

1.49

 Ability

1.48

 Capacity

1.46

能力

1.45

Activations Density 2.389%

words related to scientific studies of chemical and biological properties, especially those that are beneficial or have potential.

ability

No Comments

No Known Activations