INDEX

Explanations

patterns that involve geometrical concepts, or that are about slot machines

oai_token-act-pair · gemini-2.0-flash

rows and lines

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Portale

-0.75

contentLoaded

-0.68

 Signalez

-0.59

Personendaten

-0.59

 initComponents

-0.58

__':

-0.56

 marshmallows

-0.55

jstor

-0.55

 }}"></

-0.54

 Waray

-0.54

POSITIVE LOGITS

row

0.91

 line

0.76

 rows

0.75

 lines

0.74

Row

0.73

 Lines

0.70

 fila

0.68

 LINE

0.67

 Line

0.67

LINE

0.66

Activations Density 1.066%

patterns that involve geometrical concepts, or that are about slot machines

rows and lines

No Comments

No Known Activations