INDEX

Explanations

question marks and other characters commonly used in questions and answers on internet forums

oai_token-act-pair · gemini-2.0-flash

question mark

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

 مرئيه

-0.95

 <=",

-0.94

__*/

-0.86

keyColumn

-0.86

NameInMap

-0.85

 OFDb

-0.83

GEBURTS

-0.82

 kaarangay

-0.82

Portail

-0.81

 محفوظة

-0.80

POSITIVE LOGITS

any

0.71

Any

0.67

Any

0.63

 thanks

0.59

any

0.57

 thank

0.49

 Thank

0.49

 Thanks

0.47

 grazie

0.47

 grâce

0.46

Activations Density 2.229%

question marks and other characters commonly used in questions and answers on internet forums

question mark

No Comments

No Known Activations

question marks and other characters commonly used in questions and answers on internet forums

question mark

No Comments

No Known Activations