INDEX

Explanations

the word "you" alongside other words

oai_token-act-pair · gemini-2.0-flash

you

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Préférences

-0.49

PACS

-0.47

atterson

-0.46

 Bioaccumulative

-0.45

UrlEncoded

-0.44

BBA

-0.44

httphttps

-0.43

principalColumn

-0.43

ynomial

-0.42

TestingModule

-0.41

POSITIVE LOGITS

 saved

0.63

 guys

0.62

Искәрмәләр

0.60

googleapis

0.60

fsch

0.59

SpringRunner

0.57

TagHelper

0.56

 Saved

0.55

 Mess

0.54

 Савезне

0.54

Activations Density 0.349%

the word "you" alongside other words

you

No Comments

No Known Activations