© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63648
    Prev
    Next
    INDEX
    Explanations

    say "["

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Administración
    0.38
    ව්
    0.37
     ОТ
    0.37
    UTER
    0.36
     Ot
    0.36
     Ruch
    0.35
    UTHER
    0.35
    銷
    0.34
     lepro
    0.34
    isent
    0.33
    POSITIVE LOGITS
     ہمیں
    0.38
    स्य
    0.37
    vani
    0.36
     바랍니다
    0.36
     हमें
    0.35
     }^{*}$
    0.35
     আমাদেরকে
    0.34
    ako
    0.34
    datasets
    0.34
    iera
    0.34
    Activations Density 0.003%

    No Known Activations