INDEX

Explanations

words seemingly related to travel, politics, safety concerns, emergencies, and government operations.

oai_token-act-pair · gemini-2.0-flash

Locations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

]")]

-0.50

mybatisplus

-0.46

جغرافيا

-0.46

-0.40

hum

-0.37

 forState

-0.35

 Nearby

-0.35

 Nähe

-0.35

цвета

-0.35

Near

-0.34

POSITIVE LOGITS

存于互联网档案馆

0.79

ьаж

0.73

 mosques

0.71

بوابة

0.71

phosa

0.70



0.68

 monasteries

0.66

 riparian

0.65

 uſed

0.64

 Sardin

0.63

Activations Density 8.253%

words seemingly related to travel, politics, safety concerns, emergencies, and government operations.

Locations

No Comments

No Known Activations