INDEX

Explanations

punctuation, conjunctions, and discourse markers

oai_token-act-pair · gemini-2.0-flash

punctuation

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

 StatelessWidget

-0.63

PRNewswire

-0.59

fml

-0.56

%>%

-0.52

 orchids

-0.52

 OMIT

-0.50

さつ

-0.49

 useCallback

-0.49

 rise

-0.49

躇

-0.49

POSITIVE LOGITS

 initComponents

0.82

ValueStyle

0.64

 &___

0.60

Искәрмәләр

0.60

ftagPool

0.59

 CreateTagHelper

0.58

 ujednoznacz

0.58

copg

0.57

ագրություններ

0.56

 disambiguazione

0.56

Activations Density 2.585%

punctuation, conjunctions, and discourse markers

punctuation

No Comments

No Known Activations