INDEX

Explanations

the number two

oai_token-act-pair · gemini-2.0-flash

two

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

two

-1.94

two

-1.74

Two

-1.58

 deux

-1.36

Two

-1.34

<bos>

-1.29

TWO

-1.27

TWO

-1.18

 zwei

-1.11

 двух

-1.07

POSITIVE LOGITS

makeConstraints

0.79

 EconPapers

0.69

 Normdatei

0.69

ConstraintMaker

0.68

mybatisplus

0.68

ErrUnexpectedEOF

0.67

 numerus

0.64

 Roskov

0.60

TagMode

0.60

 Exter

0.60

Activations Density 0.596%

the number two

two

No Comments

No Known Activations