INDEX

Explanations

the word "island" and connecting words

oai_token-act-pair · gemini-2.0-flash

island

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 AssemblyTitle

-0.70

urlpatterns

-0.68

الحياه

-0.65

LayoutPanel

-0.58

bootstrapcdn

-0.56

 numberOfRows

-0.53

biz

-0.52

principalTable

-0.52

gridx

-0.51

getDoctrine

-0.51

POSITIVE LOGITS

 متعلقه

0.62

 betweenstory

0.59

angeran

0.53

oredCriteria

0.53

webElementXpaths

0.52

 EconPapers

0.52

 defaultstate

0.51

verley

0.48

jacks

0.48

Попис

0.48

Activations Density 1.195%

the word "island" and connecting words

island

No Comments

No Known Activations