INDEX

Explanations

words or phrases related to family or social connections

oai_token-act-pair · gemini-2.0-flash

spouses

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

<bos>

-0.70

WebElementEntity

-0.48

ämä

-0.46

CHELL

-0.46

 gebra

-0.44

بال

-0.43

['

-0.42

cives

-0.42

ázquez

-0.41

五行

-0.39

POSITIVE LOGITS

SharedCtor

0.77

 ChromeDriver

0.69

basicConfig

0.65

 Wikimedijinoj

0.60

SpringBootTest

0.59

 createState

0.59

BeginContext

0.58

 wireType

0.56

 initComponents

0.55

 sumpay

0.55

Activations Density 0.081%

words or phrases related to family or social connections

spouses

No Comments

No Known Activations

words or phrases related to family or social connections

spouses

No Comments

No Known Activations