© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41482
    Prev
    Next
    INDEX
    Explanations

    geographical coordinates

    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_22_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
    Ⲛ
    0.39
     introns
    0.37
    ણા
    0.36
    еты
    0.36
    է
    0.35
    retched
    0.35
     precept
    0.35
    ธ์
    0.34
     tcpHeader
    0.34
    Mn
    0.34
    POSITIVE LOGITS
     búsqueda
    0.44
     tended
    0.40
     caracteriza
    0.40
     paddock
    0.40
    oll
    0.38
    io
    0.38
     são
    0.38
     শ
    0.38
     cubierta
    0.38
     Port
    0.37
    Activations Density 0.005%

    No Known Activations