INDEX

Explanations

words related to international politics and conflict, particularly involving Russia, Ukraine, and economic sanctions.

oai_token-act-pair · gemini-2.0-flash

political tensions

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

Negative Logits

 Bakers

-0.58

 itſelf

-0.57

 turística

-0.56

 Counters

-0.56

 Missy

-0.55

 myſelf

-0.54

 Wyndham

-0.52

 themſelves

-0.51

TintMode

-0.51

 fabia

-0.50

POSITIVE LOGITS

setupUi

0.61

[]:

0.61

Ren

0.55

Ren

0.55

︎

0.54

ayas

0.49

zade

0.49

vis

0.47

NavController

0.46

TabLayout

0.46

Activations Density 13.456%

words related to international politics and conflict, particularly involving Russia, Ukraine, and economic sanctions.

political tensions

No Known Activations