INDEX

Explanations

words related to medical procedures applied to the body

oai_token-act-pair · gemini-2.0-flash

wound and tissue repair

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

enderror

-0.77

ⓧ

-0.74

ReusableCell

-0.74

 насељу

-0.73

 censiti

-0.73

 ExecuteAsync

-0.72

enumi

-0.70

 تضيفلها

-0.69

 समीक्षक

-0.69

Hochspringen

-0.68

POSITIVE LOGITS

pen

0.48

 Union

0.48

nal

0.48

ul

0.48

stamo

0.47

mal

0.46

ind

0.44

ด

0.43

 union

0.43

 site

0.43

Activations Density 5.621%

words related to medical procedures applied to the body

wound and tissue repair

No Known Activations