INDEX

Explanations

references to the senses, especially sight and taste

oai_token-act-pair · gemini-2.0-flash

Attention/Eyes

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

 eyes

-0.92

 Eyes

-0.85

 EYES

-0.80

 sight

-0.79

Eyes

-0.76

eye

-0.76

Hearing

-0.72

Eye

-0.72

 Hearing

-0.70

Eye

-0.69

POSITIVE LOGITS

RectangleBorder

0.47

脚注の使い方

0.47

سكرية

0.45

цездатний

0.44

كذا

0.44

tivism

0.43

iatric

0.43

ViewImports

0.43

những

0.42

tamine

0.42

Activations Density 1.402%

references to the senses, especially sight and taste

Attention/Eyes

No Comments

No Known Activations