INDEX

Explanations

mentions of positions, status, and affiliations of people

oai_token-act-pair · gemini-2.0-flash

Identifying people/things

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

IsPostBack

-0.56

/***/

-0.55

 ComVisible

-0.54

__(/*!

-0.54



-0.52

BindView

-0.51

ритори

-0.51

URLException

-0.49

 المعيارى

-0.49

LogFactory

-0.49

POSITIVE LOGITS

 täh

0.57

latego

0.54

WebControls

0.54

Jeografia

0.54

réhen

0.54

 scatola

0.52

 Bioaccumulative

0.52

rugated

0.52

 Præ

0.50

شوف

0.50

Activations Density 24.853%

mentions of positions, status, and affiliations of people

Identifying people/things

No Comments

No Known Activations