INDEX

Explanations

words and phrases related to business and technology advertising

oai_token-act-pair · gemini-2.0-flash

finding, searching

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

ofür

-0.58

//

-0.57

Datuak

-0.55

ysacchar

-0.54

andExpect

-0.53

 Meksiku

-0.53

Rüyada

-0.52

ời

-0.52

<()>

-0.51

ynch

-0.50

POSITIVE LOGITS

 finding

1.45

Finding

1.28

finding

1.27

 find

1.26

 Finding

1.25

 searching

1.23

 search

1.20

Find

1.19

find

1.19

 finds

1.14

Activations Density 2.406%

words and phrases related to business and technology advertising

finding, searching

No Comments

No Known Activations