INDEX

Explanations

a variety of special characters or formatting common to academic publications

oai_token-act-pair · gemini-2.0-flash

Technical writing

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

UnusedPrivate

-0.69

Tikang

-0.62

enderror

-0.46

Pautan

-0.45

 otomatig

-0.44

러나

-0.44

XmlAccessType

-0.43

(&:

-0.43

 мәкал

-0.43

netbeans

-0.42

POSITIVE LOGITS

InlineData

0.59

 CreateTagHelper

0.54

ঙ্গ

0.51

 sockaddr

0.51

 arşivlendi

0.50

 Wayback

0.50

PerformLayout

0.49

 Taub

0.49

addComponent

0.49

 Reserv

0.49

Activations Density 3.028%

a variety of special characters or formatting common to academic publications

Technical writing

No Comments

No Known Activations