INDEX

Explanations

words related to edges, boundaries, and borders, often in a physical or graphical sense

oai_token-act-pair · gemini-2.0-flash

borders/edges

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 متعلقه

-0.75

 مشين

-0.72

 AssemblyProduct

-0.70

 utafitiHapana

-0.67

ISupport

-0.64

AddHtmlAttribute

-0.63

Cyfeiriadau

-0.59

 Edge

-0.59

ValueStyle

-0.58

 CURIAM

-0.58

POSITIVE LOGITS

MessageOf

0.59

ValueGeneration

0.56

 surla

0.50

INSEE

0.49

detta

0.44

 between

0.44

ChildScrollView

0.42

 між

0.41

########.

0.40

 mezi

0.40

Activations Density 5.566%

words related to edges, boundaries, and borders, often in a physical or graphical sense

borders/edges

No Comments

No Known Activations