INDEX

Explanations

people including their titles, positions, and political affiliations

oai_token-act-pair · gemini-2.0-flash

politics and government

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

nip

-0.49

 jsPsych

-0.49

mazoo

-0.46

uolo

-0.45

 بيها

-0.44

latte

-0.43

 Faso

-0.43

 Baillargeon

-0.43

lanzen

-0.42

Demografia

-0.42

POSITIVE LOGITS

 autorytatywna

0.65

Autoritní

0.61

QMetaType

0.61

fören

0.61

:✨

0.59

ReusableCell

0.58

__':

0.55

thâu

0.55

참고

0.51

日閲覧

0.51

Activations Density 1.144%

people including their titles, positions, and political affiliations

politics and government

No Comments

No Known Activations