INDEX

Explanations

image links within HTML paragraph tags that contain the word "full" in the image title

oai_token-act-pair · gemini-2.0-flash

full

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

rrggbb

-0.57

deelte

-0.55

 jScrollPane

-0.52

 Roskov

-0.52

licula

-0.50

bootstrapcdn

-0.50

 keyPressed

-0.49

 InputDecoration

-0.49

EndProject

-0.49

lwjgl

-0.48

POSITIVE LOGITS

<bos>

1.02

Rüyada

0.73

Datuak

0.68

 ioutil

0.64

 coûte

0.63

 morire

0.62

ніципа

0.60

 kaarangay

0.59

 câte

0.59

клопе

0.58

Activations Density 0.333%

image links within HTML paragraph tags that contain the word "full" in the image title

full

No Comments

No Known Activations