INDEX

Explanations

text describing the invention and function of devices

oai_token-act-pair · gemini-2.0-flash

process

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

inventions and processes

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

protoimpl

-0.90

setVerticalGroup

-0.82

rrggbb

-0.82

цездатний

-0.73

sizeCache

-0.73

 مشين

-0.69

Diwedd

-0.68

таратура

-0.65

Vidite

-0.64

 beginnetje

-0.63

POSITIVE LOGITS

 مق

0.49

 lead

0.48

Lead

0.47

 release

0.45

kapet

0.45

LayoutStyle

0.44

XmlType

0.44

 Lead

0.43

alcool

0.43

taciones

0.43

Activations Density 5.203%

text describing the invention and function of devices

process

inventions and processes

No Comments

No Known Activations