INDEX

Explanations

a mix of words referring to food, table data, and italian names

oai_token-act-pair · gemini-2.0-flash

Italian Language

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

Not in Any Lists

No Comments

Negative Logits

oa̍t

-0.67

Jegyzetek

-0.66

Hochspringen

-0.63

ConstraintMaker

-0.60

TestingModule

-0.60

buttonBar

-0.60

oneofs

-0.60

Autoritní

-0.59

 jspb

-0.59

ReusableCell

-0.58

POSITIVE LOGITS

alnız

0.47

NSIndexPath

0.47

atsby

0.46

 kív

0.46

spaceBetween

0.46

 darbo

0.43

ależy

0.43

 propriétés

0.42

 spac

0.41

 TableColumn

0.40

Activations Density 0.353%

a mix of words referring to food, table data, and italian names

Italian Language

No Comments

No Known Activations