INDEX

Explanations

gibberish

np_token-act-pair-logits · gemini-2.0-flash

partner

np_max-act-logits · gemini-2.0-flash

words related to personal relationships and family

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

脚注の使い方

-0.80

expandindo

-0.68

IsContent

-0.68

出版年

-0.67

InputBorder

-0.66

ImageContext

-0.63

 незавершена

-0.63

Portail

-0.62

 صوتيه

-0.62

 CreateTagHelper

-0.60

POSITIVE LOGITS

rescence

0.47

 Kluwer

0.47

ียง

0.46

 descomp

0.45

iography

0.45

 مفص

0.45

macs

0.45

maca

0.44

glers

0.44

 considérons

0.44

Activations Density 1.163%

gibberish

partner

words related to personal relationships and family

No Comments

No Known Activations