INDEX

Explanations

words related to the framing and matting of pictures

oai_token-act-pair · gemini-2.0-flash

Furniture and materials

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 mukana

-0.66

 FetchType

-0.63

tableFuture

-0.62

 alimentaires

-0.60

Viitteet

-0.59

 Мексичка

-0.57

DECREF

-0.57

ukses

-0.57

 kokona

-0.56

 actifs

-0.56

POSITIVE LOGITS

expandindo

0.58

She

0.47

 addSubview

0.47

Diweddarwch

0.46

̍t

0.43

 night

0.41

новниш

0.41

0.40

Lee

0.40

 deut

0.40

Activations Density 1.385%

words related to the framing and matting of pictures

Furniture and materials

No Comments

No Known Activations