INDEX

Explanations

words related to scientific research, especially medical and physics related

oai_token-act-pair · gemini-2.0-flash

scientific/technical documents

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

ⓘ

-0.46

 henvisninger

-0.46

исленность

-0.44

>):

-0.43

readFileSync

-0.43

))[

-0.43

 quadruple

-0.43

kháu

-0.43

xos

-0.42

__))

-0.42

POSITIVE LOGITS

expandindo

0.79

المناصب

0.75

 فريبيس

0.69

󠁢

0.65

 Houſe

0.65

InstrumentedTest

0.64

 समीक्षक

0.64

 rospy

0.63

ghijklmnop

0.62

 myſelf

0.60

Activations Density 7.058%

words related to scientific research, especially medical and physics related

scientific/technical documents

No Comments

No Known Activations