© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43965
    Prev
    Next
    INDEX
    Explanations

    Ingebrigtsen, AngelList, Lopez

    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
    cción
    0.63
    DVRIP
    0.60
    áty
    0.56
    p
    0.56
     αυτό
    0.54
     phận
    0.54
     INTERRUPTION
    0.54
    pción
    0.53
    ']))->
    0.52
    рия
    0.51
    POSITIVE LOGITS
    و
    0.87
    ו
    0.86
    er
    0.81
    یی
    0.81
    ার
    0.70
    3
    0.68
    ي
    0.66
    4
    0.65
    il
    0.64
    //
    0.64
    Activations Density 0.001%

    No Known Activations