© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3264
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     отдельные
    0.71
    쫌
    0.69
    ০০০
    0.67
     ilang
    0.66
     militants
    0.64
    phere
    0.64
     ANGELES
    0.62
     ticks
    0.61
    vam
    0.59
    plt
    0.58
    POSITIVE LOGITS
    ů
    0.68
    ы
    0.64
    tains
    0.62
     ため
    0.60
    ્સ
    0.60
    NonUser
    0.60
    ه
    0.60
    ского
    0.59
    ता
    0.59
    یە
    0.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.