© 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. 50361
    Prev
    Next
    INDEX
    Explanations

    eye-catching designs

    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
     is
    0.87
    مر
    0.77
    has
    0.76
    is
    0.69
     has
    0.69
    d
    0.68
    the
    0.67
    in
    0.64
    a
    0.64
    main
    0.63
    POSITIVE LOGITS
     Cnemidophorus
    0.74
     Ι
    0.70
     🥰
    0.66
    uada
    0.63
     📫
    0.62
     плав
    0.62
     probiotics
    0.62
     fillets
    0.62
     忄
    0.62
     І
    0.61
    Activations Density 0.000%

    No Known Activations