INDEX

Explanations

words related to direction, location, or origin

oai_token-act-pair · gemini-2.0-flash

Prepositions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Personendaten

-0.70

تقاوى

-0.66

 незавершена

-0.60

PreExecute

-0.57

 Signalez

-0.56

LayoutPanel

-0.54

 <<<<<<<<<<<<<<

-0.53

hObject

-0.52

InjectAttribute

-0.52

SourceChecksum

-0.50

POSITIVE LOGITS

 CreateTagHelper

0.62

jectures

0.57

 albicans

0.54

acji

0.52

IUrlHelper

0.51

bcryptjs

0.51

 vorne

0.51

 springfox

0.50

éroport

0.50

 сверху

0.50

Activations Density 0.585%

words related to direction, location, or origin

Prepositions

No Comments

No Known Activations