INDEX

Explanations

hexadecimal code sequences

oai_token-act-pair · gemini-2.0-flash

+ or :

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

لیس

-0.55

 disobedience

-0.54

 Cæsar

-0.54

 coughs

-0.53

Rhestr

-0.53

 Cassini

-0.53

 ambulances

-0.52

 crucifixion

-0.52

GraphicsUnit

-0.51

 sneezing

-0.51

POSITIVE LOGITS

IntoConstraints

0.72

 Савезне

0.69

ElementException

0.66

rawDesc

0.59

 الرياضيه

0.59

 Biôgrafia

0.57

ंदीखरीदारी

0.54

tvguidetime

0.54

kwds

0.52

Activations Density 6.211%

hexadecimal code sequences

+ or :

No Comments

No Known Activations