© 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. 45449
    Prev
    Next
    INDEX
    Explanations

    brooklyn bridge

    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
    <0x9D>
    0.65
     Ն
    0.65
     эш
    0.64
    সঙ্গত
    0.63
     lluv
    0.63
    oline
    0.63
     дизай
    0.62
     distrib
    0.61
    ̩
    0.61
     elegante
    0.61
    POSITIVE LOGITS
    Pentru
    0.89
     Também
    0.81
     Tüm
    0.79
    τα
    0.77
    ের
    0.76
    iciência
    0.75
    to
    0.73
    Harga
    0.73
    PERSONAL
    0.70
    Dü
    0.70
    Activations Density 0.000%

    No Known Activations