INDEX

Explanations

the word "register" in different forms

oai_token-act-pair · gemini-2.0-flash

registered

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-1.77

 myſelf

-1.73

 Majefty

-1.70

 Monfieur

-1.65

 doubtnut

-1.61

 Houſe

-1.60

 Anſ

-1.60

 pleaſure

-1.59

 ſeveral

-1.55

 Diſ

-1.55

POSITIVE LOGITS

1.23

The

1.14

↵↵

1.13

1.05

1.02

1.00

0.89

in

0.86

0.85

0.84

Activations Density 1.795%

the word "register" in different forms

registered

No Comments

No Known Activations