INDEX

Explanations

numerical data combined with related terms, such as units of measure, percentages, or financial terminology.

oai_token-act-pair · gemini-2.0-flash

seemingly random strings of numbers

np_token-act-pair-logits · gemini-2.0-flash

Digits

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

setVerticalGroup

-0.81

 autorytatywna

-0.78

ModelAdmin

-0.72

 Roskov

-0.72

 initComponents

-0.71

Autoritní

-0.71

CppMethod

-0.71

styleType

-0.69

 fieldNum

-0.68

Дереккөздер

-0.67

POSITIVE LOGITS

 ويكيميديا

0.52

chyma

0.40

autoFocus

0.39

 éché

0.39

copyTo

0.39

sat

0.38

ejb

0.38

 Vehicle

0.38

mbals

0.38

papers

0.37

Activations Density 2.497%

numerical data combined with related terms, such as units of measure, percentages, or financial terminology.

seemingly random strings of numbers

Digits

No Comments

No Known Activations