INDEX

Explanations

technical documents using words like "version", "data", and names of software

oai_token-act-pair · gemini-2.0-flash

programming/computing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

linker

-0.56

EndInit

-0.48

joi

-0.47

MigrationBuilder

-0.46

Kontrola

-0.46

 UnityEditor

-0.45

 emend

-0.44

Materiał

-0.43

aks

-0.43

insics

-0.43

POSITIVE LOGITS

LookAnd

0.65

WebServlet

0.62

 autorytatywna

0.54

numerusform

0.54

ChildScrollView

0.52

ovec

0.52

alyptus

0.50

enumi

0.50

 שוליים

0.50

 pescoço

0.50

Activations Density 5.176%

technical documents using words like "version", "data", and names of software

programming/computing

No Comments

No Known Activations