INDEX

Explanations

the word "Bold" occurring in what appears to be code

oai_token-act-pair · gemini-2.0-flash

font styling

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

########.

-0.62

 myſelf

-0.60

 CreateTagHelper

-0.58

 itſelf

-0.56

abestanden

-0.54

neſs

-0.54

 ſeveral

-0.54

 themſelves

-0.54

脚注の使い方

-0.53

Geplaatst

-0.53

POSITIVE LOGITS

astify

0.57

mmu

0.52

UserScript

0.51

Net

0.50

 Netz

0.50

χν

0.50

ImageIO

0.49

 Regel

0.48

var

0.48

ulto

0.48

Activations Density 0.722%

the word "Bold" occurring in what appears to be code

font styling

No Comments

No Known Activations