© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206830
    Prev
    Next
    INDEX
    Explanations

    lens and lentils

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    in
    1.27
    ar
    0.91
    的
    0.78
    u
    0.72
    कालीन
    0.71
    il
    0.70
    uigen
    0.69
    inja
    0.68
    ots
    0.66
    ের
    0.65
    POSITIVE LOGITS
     lens
    0.98
    ку
    0.83
    не
    0.80
     lenses
    0.79
    Lens
    0.78
     impart
    0.74
     Lens
    0.74
    ير
    0.73
    ৮
    0.72
     ז
    0.71
    Activations Density 0.020%

    No Known Activations