INDEX

Explanations

mentions of boycotts and bans.

oai_token-act-pair · gemini-2.0-flash

co

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

]();

-0.53

Unnamed

-0.53

 RoutedEventArgs

-0.50

 tjen

-0.47

 joindre

-0.47

 übrig

-0.46

TeV

-0.46

 realizzazione

-0.45

deletion

-0.45

θεν

-0.44

POSITIVE LOGITS

 boycott

0.76

 embargo

0.73

 استنادى

0.63

 imposed

0.63

antaine

0.62

 boycot

0.61

openConnection

0.61

WaitGroup

0.60

SuccessListener

0.60

 resultCode

0.59

Activations Density 1.039%

mentions of boycotts and bans.

co

No Comments

No Known Activations