INDEX

Explanations

words that indicate location, public use, lack of something, or amounts from very different topics

oai_token-act-pair · gemini-2.0-flash

using

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

use

-0.53

(;;)

-0.52

 (;;)

-0.49

 Usage

-0.49

use

-0.48

USE

-0.46

USAGE

-0.44

Use

-0.44

ạo

-0.43

Use

-0.42

POSITIVE LOGITS

 using

2.77

 Using

2.30

using

2.25

 USING

2.23

Using

2.23

 utilizzando

1.98

 utilizando

1.97

 usando

1.90

 utilizing

1.77

 используя

1.77

Activations Density 8.816%

words that indicate location, public use, lack of something, or amounts from very different topics

using

No Comments

No Known Activations

words that indicate location, public use, lack of something, or amounts from very different topics

using

No Comments

No Known Activations