INDEX

Explanations

symbols and notation appearing in theoretical physics formulas

oai_token-act-pair · gemini-2.0-flash

physics research

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

__':

-0.88

__":

-0.86

__':

-0.84

__":

-0.71

 AssemblyCulture

-0.61

 незавершена

-0.60

featureID

-0.59

#+#

-0.58

PageIndex

-0.57

Xna

-0.55

POSITIVE LOGITS

 maestra

0.55

 Occidente

0.54

ñores

0.54

 mijne

0.52

errHandler

0.48

Vu

0.47

Barg

0.47

ListItemIcon

0.46

 mouvement

0.46

 pijn

0.46

Activations Density 2.377%

symbols and notation appearing in theoretical physics formulas

physics research

No Comments

No Known Activations