© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201673
    Prev
    Next
    INDEX
    Explanations

    Cana, pruning, Vanaheim

    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_6_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
     be
    0.87
    )
    0.82
     It
    0.75
     to
    0.73
     and
    0.69
     at
    0.67
    টি
    0.66
    '
    0.64
     was
    0.64
     এ
    0.63
    POSITIVE LOGITS
    t
    1.00
     Yatha
    0.91
     Aeonium
    0.82
     Основ
    0.81
    thed
    0.80
     Maugin
    0.80
    ت
    0.80
    ла
    0.79
     Мето
    0.79
     Omphalodes
    0.79
    Activations Density 0.000%

    No Known Activations