INDEX

Explanations

mathematical notation

oai_token-act-pair · gemini-2.0-flash

mathematical equations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 nakalista

-0.78

 <>",

-0.69

urlpatterns

-0.64

DockStyle

-0.63

Билгалдахарш

-0.61

BagLayout

-0.59

المناصب

-0.58

BeforeClass

-0.57

 protoimpl

-0.56

MigrationBuilder

-0.56

POSITIVE LOGITS

 betweenstory

0.49

0.46

 Estudiantes

0.44

CurrentValue

0.44

 Roost

0.44

 Templ

0.44

hts

0.43

 pens

0.43

ньому

0.43

Activations Density 4.397%

mathematical notation

mathematical equations

No Comments

No Known Activations