INDEX

Explanations

spanish language stop words common in questions or introductions

oai_token-act-pair · gemini-2.0-flash

en

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

 BoxFit

-1.03

########.

-0.71

IBAction

-0.64

__*/

-0.63

HtmlAttribute

-0.58

ImageContext

-0.58

 order

-0.57

Efq

-0.57

شهاد

-0.56

 addition

-0.55

POSITIVE LOGITS

principalTable

0.81

SourceChecksum

0.65

Personensuche

0.52

 ferma

0.46

IBinder

0.45

CreateIndex

0.43

 covenants

0.42

Referències

0.42

 useSelector

0.41

\|

0.41

Activations Density 0.338%

spanish language stop words common in questions or introductions

en

No Comments

No Known Activations