INDEX

Explanations

words related to activities such as traveling, relaxing, or visiting places

oai_token-act-pair · gemini-2.0-flash

could

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 trade

-0.52

 TRADE

-0.49

談

-0.47

tiliz

-0.47

 Book

-0.47

Trade

-0.46

TRADE

-0.46

 Estre

-0.46

trade

-0.45

 vlasy

-0.45

POSITIVE LOGITS

 Roskov

0.72

ⓧ

0.71

 pinulongan

0.71

참고

0.69

новниш

0.66

 Мексичка

0.64

ISupport

0.64

DeleteBehavior

0.63

MemoryWarning

0.62

љено

0.60

Activations Density 5.982%

words related to activities such as traveling, relaxing, or visiting places

could

No Comments

No Known Activations