INDEX

Explanations

words or phrases related to logins and accounts

oai_token-act-pair · gemini-2.0-flash

log

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

 للمعارف

-0.56

)_/¯

-0.54

Palmarès

-0.52

 שוליים

-0.51

 user

-0.49

用戶

-0.49

Logged

-0.48

login

-0.48

 utilisateur

-0.48

statin

-0.47

POSITIVE LOGITS

ImageContext

0.64

ValueStyle

0.63

awtextra

0.61

PMailer

0.61

bootstrapcdn

0.59

ThroughAttribute

0.57

 propOrder

0.56

HandlerContext

0.51

addTab

0.51

 Confucian

0.49

Activations Density 0.634%

words or phrases related to logins and accounts

log

No Comments

No Known Activations