© 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. 46188
    Prev
    Next
    INDEX
    Explanations

    places and associated people

    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
    on
    0.84
    et
    0.69
    PUR
    0.64
    :
    0.63
    em
    0.63
    TMP
    0.63
    AS
    0.62
    EM
    0.62
    Have
    0.62
    ಿತು
    0.61
    POSITIVE LOGITS
     in
    0.68
    ων
    0.63
    ра
    0.62
    یل
    0.61
    ری
    0.59
    п
    0.58
    یم
    0.57
     образом
    0.57
     settimane
    0.56
    خ
    0.55
    Activations Density 0.001%

    No Known Activations