INDEX

Explanations

references to the European Union

oai_token-act-pair · gemini-2.0-flash

EU

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

原始内容存档于

-0.61

όμε

-0.60

 nakalista

-0.54

AndEndTag

-0.52

ulage

-0.51

DropTable

-0.50

waltung

-0.49

rition

-0.49

igera

-0.48

enfone

-0.48

POSITIVE LOGITS

 المعيارى

0.63

awtextra

0.61

 thicken

0.57

 transférez

0.56

}}/>

0.56

 transfieras

0.55

tanleria

0.54

adpleegd

0.54

 viewDidLoad

0.54

ForRow

0.53

Activations Density 1.361%

references to the European Union

EU

No Comments

No Known Activations