INDEX

Explanations

code snippets related to XML parsing and object property manipulation, possibly including French terms

oai_token-act-pair · gemini-2.0-flash

code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 provato

-0.43

fromnode

-0.42

 kasarigan

-0.40

OrBuilder

-0.40

windowFixed

-0.39

etsk

-0.39

 Réponses

-0.39

rovnik

-0.38

 provare

-0.38

ználat

-0.38

POSITIVE LOGITS

AutoScaleMode

0.71

]--;

0.70

دانشنامهٔ

0.69

ImageContext

0.67

HasAnnotation

0.67

Coordonnées

0.66

]));

0.66

zyj

0.65

'},

0.64

Activations Density 13.578%

code snippets related to XML parsing and object property manipulation, possibly including French terms

code

No Comments

No Known Activations