© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9849
    Prev
    Next
    INDEX
    Explanations

    hot spring resort

    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_13_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
     poumon
    0.69
    㓩
    0.65
    导弹
    0.59
    㸮
    0.59
    籿
    0.58
     而且
    0.58
     सुनेंरोक
    0.58
     conteú
    0.57
    MyToolkit
    0.57
    rootScope
    0.57
    POSITIVE LOGITS
    els
    0.70
    ↵
    0.70
    ال
    0.70
    el
    0.66
    “
    0.65
     “
    0.63
    k
    0.61
    +
    0.61
     or
    0.61
    CL
    0.60
    Activations Density 0.016%

    No Known Activations