INDEX

Explanations

words related to systems, accounts, or processes being registered within a larger network or database

oai_token-act-pair · gemini-2.0-flash

register

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 register

-2.64

 registering

-2.39

 registered

-2.39

 registration

-2.38

 registers

-2.34

 Register

-2.33

 REGISTER

-2.28

register

-2.27

Register

-2.20

 Registration

-2.19

POSITIVE LOGITS

NOPQRST

0.53

svet

0.47

@[

0.46

ẩm

0.45

Nac

0.44

 posible

0.44

mgang

0.44

teto

0.44

待

0.43

 Auss

0.43

Activations Density 9.212%

words related to systems, accounts, or processes being registered within a larger network or database

register

No Comments

No Known Activations