INDEX

Explanations

the articles 'a' and 'an'.

oai_token-act-pair · gemini-2.0-flash

a

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

few

-0.45

abord

-0.44

EndOf

-0.43

一二

-0.42

Few

-0.42

few

-0.41

some

-0.41

তথ্যসূত্র

-0.41

Some

-0.41

 multitude

-0.40

POSITIVE LOGITS

脚注の使い方

0.90

Tembelea

0.88

 createState

0.84

posedge

0.84

NameInMap

0.84

 AssemblyCompany

0.75

 дописавши

0.74

 CommonModule

0.74

)");

0.73

oredCriteria

0.73

Activations Density 2.712%

the articles 'a' and 'an'.

a

No Comments

No Known Activations