INDEX

Explanations

words related to research studies and scientific language, including medical terms, but not consistently

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

########.

-1.01

 betweenstory

-0.90

 confiable

-0.84

 '\\;'

-0.78

 parlor

-0.78

 favors

-0.77

 beginnetje

-0.76

 equalization

-0.76

 >=",

-0.76

 favorably

-0.75

POSITIVE LOGITS

Whilst

1.10

 Whilst

1.04

 specialises

0.95

 whilst

0.91

centred

0.89

 recognised

0.88

initialise

0.88

 analysed

0.88

 centre

0.87

centre

0.86

Activations Density 1.302%

words related to research studies and scientific language, including medical terms, but not consistently

No Comments

No Known Activations