INDEX

Explanations

German words

oai_token-act-pair · gemini-2.0-flash

mostly German language

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

 للاسماء

-0.77

RTLD

-0.63

 oprot

-0.62

arraycopy

-0.61

RectangleBorder

-0.60

__.__

-0.59

 Voyez

-0.59

 كومونز

-0.56

ombic

-0.56

 Independencia

-0.54

POSITIVE LOGITS

urlpatterns

0.53

AddTagHelper

0.53

kháu

0.51

PyErr

0.49

 AttributeSet

0.45

att

0.43

 InputDecoration

0.43

 indisponible

0.42

#![

0.42

 defaultstate

0.40

Activations Density 1.040%

German words

mostly German language

No Comments

No Known Activations