© 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. 9074
    Prev
    Next
    INDEX
    Explanations

    endocytosis and budding

    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
    Sud
    0.58
    Tx
    0.51
     उड़ा
    0.51
    Ef
    0.50
    ?”.
    0.48
    EOS
    0.48
    柇
    0.48
    SX
    0.47
    緊張
    0.47
    regation
    0.46
    POSITIVE LOGITS
    শিকান্ত
    0.60
    at
    0.54
     keepsake
    0.53
     covalently
    0.52
    ার্টমেন্ট
    0.49
     thei
    0.48
     جیسا
    0.48
     periodical
    0.47
    amodel
    0.47
     elasticity
    0.46
    Activations Density 0.005%

    No Known Activations