INDEX

Explanations

words related to scientific methods, statistics, and programming

oai_token-act-pair · gemini-2.0-flash

use, usage

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

меч

-0.48

 berke

-0.39

 schließen

-0.39

ыгана

-0.39

っこ

-0.39

onne

-0.38

об

-0.38

клопе

-0.36

SARA

-0.36

็จ

-0.36

POSITIVE LOGITS

use

1.40

 usage

1.38

 Usage

1.24

 usages

1.19

 utilization

1.19

use

1.18

uso

1.16

 utilisation

1.16

Use

1.15

Use

1.15

Activations Density 1.810%

words related to scientific methods, statistics, and programming

use, usage

No Comments

No Known Activations