© 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. 126684
    Prev
    Next
    INDEX
    Explanations

    well-meaning but

    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
    ﺭ
    0.71
    ן
    0.68
    startsWith
    0.63
    முறை
    0.61
    nard
    0.61
     பிரபு
    0.61
    nz
    0.60
    that
    0.60
    naive
    0.59
     ಕ್ರಮ
    0.58
    POSITIVE LOGITS
     è
    0.77
     to
    0.71
    ang
    0.68
     be
    0.67
     of
    0.66
     interpersonal
    0.66
    ø
    0.64
     แต่
    0.63
     are
    0.63
     में
    0.63
    Activations Density 0.000%

    No Known Activations