INDEX

Explanations

words from a language other than English

oai_token-act-pair · gemini-2.0-flash

mobile app UI text

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

mybatisplus

-0.79

-0.77

 دیکھیے

-0.73

NameInMap

-0.71

styleType

-0.71

DrawerToggle

-0.70

+#+#

-0.69

SourceChecksum

-0.68

endphp

-0.68

}))

-0.68

POSITIVE LOGITS

esi

0.43

zewod

0.41

Raptor

0.40

jer

0.39

der

0.38

jem

0.36

istique

0.36

发表于

0.36

 TestBed

0.35

 réduction

0.35

Activations Density 0.425%

words from a language other than English

mobile app UI text

No Comments

No Known Activations