INDEX

Explanations

mentions of geopolitical events involving governments overthrowing other governments.

oai_token-act-pair · gemini-2.0-flash

historical events

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IndentedString

-0.92

:✨

-0.79

 comigo

-0.74

DockStyle

-0.71

argout

-0.67

 eighties

-0.65

 Мексичка

-0.64

 conmigo

-0.64

 esternos

-0.64

 énergé

-0.63

POSITIVE LOGITS

 Beat

0.47

fir

0.44

 firm

0.43

 PackageManager

0.43

WebElementEntity

0.42

Fif

0.42

 DbContext

0.41

cinia

0.41

sizeCache

0.41

IBinder

0.41

Activations Density 1.150%

mentions of geopolitical events involving governments overthrowing other governments.

historical events

No Comments

No Known Activations