INDEX

Explanations

multiple references to locations and people in China including Chinese characters

oai_token-act-pair · gemini-2.0-flash

(

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 propOrder

-0.75

<bos>

-0.71

 مشين

-0.68

.*")]

-0.67

)++;

-0.65

DeleteBehavior

-0.65

__;

-0.65

 MainAxisSize

-0.65

WithIOException

-0.64

enumi

-0.63

POSITIVE LOGITS

 enfans

0.40

 publiques

0.39

 desar

0.36

 hals

0.34

 gagné

0.33

 bílá

0.33

mű

0.32

 domestiques

0.31

 sauvages

0.31

lardır

0.31

Activations Density 0.183%

multiple references to locations and people in China including Chinese characters

(

No Comments

No Known Activations