INDEX

Explanations

years represented numerically

oai_token-act-pair · gemini-2.0-flash

Numbers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

abetes

-0.69

posedge

-0.52

MigrationBuilder

-0.51

reps

-0.50

 ISNI

-0.48

Obrázky

-0.46

setupUi

-0.46

ConstraintMaker

-0.46

TagHelpers

-0.46

 spørs

-0.45

POSITIVE LOGITS

 يتيمه

0.69

 AspNetCore

0.67

findpost

0.62

 تانيه

0.59

 CanadaChoose

0.57

 Numerology

0.57

AxisAlignment

0.52

 useRouter

0.52

{?>

0.49

存于互联网档案馆

0.49

Activations Density 2.089%

years represented numerically

Numbers

No Comments

No Known Activations