© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15963
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to ownership and/or property rights

    oai_token-act-pair · gemini-2.0-flash

    ownership and belonging

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     belonged
    -1.02
     belong
    -0.96
     belongs
    -0.91
     belonging
    -0.80
    belong
    -0.77
     pertence
    -0.76
     appartiennent
    -0.74
    HasForeignKey
    -0.69
     Belong
    -0.68
    MLLoader
    -0.66
    POSITIVE LOGITS
    省市镇
    0.52
     دیکھیے
    0.46
    ArrowToggle
    0.46
    裟
    0.45
    slidesToShow
    0.43
     sqlSession
    0.41
    IsMutable
    0.40
    참고
    0.40
     incor
    0.39
    IonicModule
    0.39
    Activations Density 2.219%

    No Known Activations