INDEX

Explanations

references to geographical landmasses, islands, and regions.

oai_token-act-pair · gemini-2.0-flash

islands

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

Negative Logits

Island

-0.96

 island

-0.96

 Island

-0.96

 ISLAND

-0.95

island

-0.89

 lenker

-0.83

 تكبرها

-0.75

 peninsula

-0.75

 '\\;'

-0.75

 nahilalakip

-0.73

POSITIVE LOGITS

an

0.57

 arqu

0.55

 arch

0.53

arch

0.53

Kep

0.49

 piccole

0.49

Arch

0.48

 Arch

0.48

 tiny

0.48

 pequeña

0.47

Activations Density 1.900%

references to geographical landmasses, islands, and regions.

islands

No Known Activations