INDEX

Explanations

the phrase "in a row"

oai_token-act-pair · gemini-2.0-flash

say "row or column"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Row

-2.23

row

-2.22

 column

-2.20

 columns

-2.19

 rows

-2.11

Row

-2.08

 Column

-2.05

 Columns

-2.02

ROW

-2.02

 Rows

-1.99

POSITIVE LOGITS

 ivelany

0.57

 lisboa

0.54

Vorlage

0.53

 getSystem

0.51

 Sist

0.51

usercontent

0.51

 estimés

0.49

χρι

0.48

Donnie

0.48

numerusform

0.47

Activations Density 0.941%

the phrase "in a row"

say "row or column"

No Comments

No Known Activations