INDEX

Explanations

uses of the word "to" alongside conjunctions and nouns, possibly related to intention and purpose

oai_token-act-pair · gemini-2.0-flash

to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 JpaRepository

-0.68

apimachinery

-0.67

 referenties

-0.64

Portale

-0.63

 peindre

-0.63

phazard

-0.62

elden

-0.60

Бахар

-0.59

Lycka

-0.59

 abstrato

-0.59

POSITIVE LOGITS

par

0.50

Ap

0.49

 AssemblyCompany

0.47

eap

0.46

SourceChecksum

0.45

__(/*!

0.44

 invokingState

0.43

ap

0.43

par

0.43

cellona

0.43

Activations Density 1.995%

uses of the word "to" alongside conjunctions and nouns, possibly related to intention and purpose

to

No Known Activations