© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211006
    Prev
    Next
    INDEX
    Explanations

    Goleman

    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_5_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
    the
    0.92
    3
    0.71
     protégé
    0.61
     the
    0.54
    ivo
    0.54
     precedent
    0.54
     complet
    0.53
     wardrobe
    0.53
     financier
    0.53
    ));
    0.52
    POSITIVE LOGITS
     It
    0.90
    is
    0.71
    ли
    0.71
    지를
    0.69
    е
    0.69
    지는
    0.68
    л
    0.66
     or
    0.66
    㗊
    0.66
    기
    0.65
    Activations Density 0.000%

    No Known Activations