© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197970
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    س
    0.67
     speciali
    0.62
     suspension
    0.59
     representation
    0.58
    ำ
    0.58
     hydrogen
    0.58
     marriage
    0.56
     hundred
    0.55
    ित
    0.54
    ล
    0.54
    POSITIVE LOGITS
     عكس
    0.70
    RO
    0.67
     Pokud
    0.62
    pkins
    0.61
    Pokud
    0.61
     уйна
    0.60
     الذه
    0.60
    c
    0.60
    aj
    0.60
     těchto
    0.60
    Activations Density 0.000%

    No Known Activations