INDEX

Explanations

words related to elections and political bodies

oai_token-act-pair · gemini-2.0-flash

government

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 catch

-0.56

خی

-0.50

mycompany

-0.49

 NDEBUG

-0.49

Extinguishing

-0.48

Bav

-0.46

mav

-0.46

née

-0.46

innis

-0.46

ova

-0.44

POSITIVE LOGITS

 مشين

0.79

Tembelea

0.70

цездатний

0.63

دانشنامهٔ

0.62

Autoritní

0.60

 censiti

0.57

RTEX

0.57

aarrggbb

0.56

MemoryWarning

0.56

enderror

0.56

Activations Density 0.727%

words related to elections and political bodies

government

No Comments

No Known Activations