© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83301
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <h2>
    0.67
    ن
    0.63
    ন
    0.57
     by
    0.55
    by
    0.55
    扡
    0.55
    㤓
    0.54
    是有
    0.53
    䓶
    0.53
    *
    0.52
    POSITIVE LOGITS
    ısı
    0.66
    ā
    0.63
    ᱑
    0.63
    ımı
    0.60
    ası
    0.60
     precisión
    0.59
    ]=\
    0.58
    ecirc
    0.58
     appreciating
    0.57
    ᱓
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.