© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86856
    Prev
    Next
    INDEX
    Explanations

    writing and drawing tools

    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_3_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
    н
    0.97
    ب
    0.95
    ر
    0.89
    ي
    0.87
    ن
    0.79
    ه
    0.79
    你
    0.78
    Ин
    0.75
    น
    0.75
    у
    0.71
    POSITIVE LOGITS
     of
    1.02
     the
    0.90
     on
    0.82
     is
    0.71
     at
    0.65
     mentor
    0.62
    ryk
    0.61
     student
    0.56
    field
    0.55
     are
    0.55
    Activations Density 0.000%

    No Known Activations