INDEX

Explanations

mathematical formulas and expressions with special symbols

oai_token-act-pair · gemini-2.0-flash

math formulas

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

Personensuche

-1.20

 الرياضيه

-0.93

########.

-0.81

PostInfinity

-0.78

ArrowToggle

-0.77

IsContent

-0.76

+#+#

-0.76

省市镇

-0.75

 betweenstory

-0.75

AsUp

-0.74

POSITIVE LOGITS

睦

0.48

Press

0.45

press

0.43

("

0.43

 بسي

0.41

онер

0.40

dvo

0.40

ApiModelProperty

0.39

 EdgeInsets

0.39

 easy

0.38

Activations Density 3.511%

mathematical formulas and expressions with special symbols

math formulas

No Comments

No Known Activations