INDEX

Explanations

language about advertising and consumers

oai_token-act-pair · gemini-2.0-flash

Marketing and consumers

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 صوتيه

-0.68

 Theſe

-0.67

 Monfieur

-0.61

 CreateTagHelper

-0.59

 vines

-0.58

 acrylique

-0.58

 Jérusalem

-0.58

 Sigism

-0.56

 photolibrary

-0.55

albero

-0.55

POSITIVE LOGITS

 arşivlendi

0.67

 consultato

0.58

 bậc

0.55

tagHelper

0.52

Autoritní

0.48

 мер

0.48

setVerticalGroup

0.48

 Wikimedijinoj

0.47

 prop

0.46

 items

0.45

Activations Density 5.049%

language about advertising and consumers

Marketing and consumers

No Comments

No Known Activations