INDEX

Explanations

mathematical notations that include 'i' as a variable with a superscript

oai_token-act-pair · gemini-2.0-flash

Non-English words

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

enterOuterAlt

-0.65

<sup>

-0.55

AutoScale

-0.54

 AssemblyCulture

-0.53

sizeCache

-0.49

principalTable

-0.49

ChildScrollView

-0.48

 Extragalactic

-0.46

 BoxDecoration

-0.45

第

-0.45

POSITIVE LOGITS

 autorytatywna

0.76

=$?

0.63

noir

0.62

 Administrativna

0.62

MLLoader

0.61

 huyền

0.54

ьажоргаш

0.54

PMailer

0.54

zysty

0.53

nessed

0.53

Activations Density 0.234%

mathematical notations that include 'i' as a variable with a superscript

Non-English words

No Comments

No Known Activations