© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4874
    Prev
    Next
    INDEX
    Explanations

    the word "preparation" and words connected to it

    oai_token-act-pair · gemini-2.0-flash

    preparation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     متعلقه
    -0.95
    preparing
    -0.76
     preparation
    -0.74
    preparation
    -0.74
     preparatory
    -0.74
    prepar
    -0.73
     rheumatism
    -0.72
     prepara
    -0.70
     Preparation
    -0.69
     Preparing
    -0.68
    POSITIVE LOGITS
    Personendaten
    0.75
    Datuak
    0.69
     autorytatywna
    0.69
    ⓧ
    0.59
    ibatis
    0.57
    ↵
    0.57
     <<<<<<<<<<<<<<
    0.57
    তথ্যসূত্র
    0.56
    Personensuche
    0.55
    Externí
    0.54
    Activations Density 1.116%

    No Known Activations