© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 193248
    Prev
    Next
    INDEX
    Explanations

    There's a

    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_27_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     letzten
    0.21
     WindowStateType
    0.19
     dwRes
    0.19
    புரம்
    0.19
     بجائے
    0.19
     atuais
    0.19
    畢
    0.18
    ╥
    0.18
     ইউনাই
    0.18
     sélectionnés
    0.18
    POSITIVE LOGITS
    with
    0.21
    function
    0.20
    which
    0.20
    any
    0.20
    hi
    0.20
    the
    0.19
    hita
    0.19
    ini
    0.18
    ct
    0.18
    ity
    0.18
    Activations Density 0.001%

    No Known Activations