INDEX

Explanations

the word "brown", sometimes associated with other colors or food items

oai_token-act-pair · gemini-2.0-flash

brown

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

 تضيفلها

-0.64

 فريبيس

-0.59

MetaObject

-0.59

parsedMessage

-0.58

ComponentModel

-0.56

 Catawiki

-0.54

AnchorStyles

-0.54

 SIMBAD

-0.51

სქოლიო

-0.51

 cappello

-0.50

POSITIVE LOGITS

Personendaten

0.63

SequentialGroup

0.56

StoryboardSegue

0.54

 دریافت‌شده

0.48

 star

0.47

 гаран

0.47

rshire

0.46

__*/

0.44

iciens

0.44

 насељу

0.43

Activations Density 0.311%

the word "brown", sometimes associated with other colors or food items

brown

No Comments

No Known Activations