INDEX

Explanations

code and configuration snippets, especially those involving URLs and JSON

oai_token-act-pair · gemini-2.0-flash

API/code related

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

Negative Logits

 générale

-0.42

by

-0.41

 Hauses

-0.40

лятор

-0.39

reszcie

-0.38

 intérieure

-0.38

ity

-0.38

 contesta

-0.38

 lịch

-0.38

 sociali

-0.37

POSITIVE LOGITS

 مشين

1.10

tagHelperRunner

1.10

EndGlobalSection

0.84

 propOrder

0.83

rungsseite

0.82

 يتيمه

0.77

UnsafeEnabled

0.77

oredCriteria

0.77

elemField

0.76

featureID

0.75

Activations Density 1.930%

code and configuration snippets, especially those involving URLs and JSON

API/code related

No Known Activations