© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75423
    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_31_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
     nooit
    0.43
    参数向量
    0.42
     colloqu
    0.40
     अपरा
    0.38
    ungy
    0.37
    LIOGRAPHY
    0.37
    ínű
    0.36
    ᒫ
    0.36
     myBuilder
    0.36
    ществ
    0.36
    POSITIVE LOGITS
    akur
    0.41
    ާއި
    0.38
    createServer
    0.37
    錯
    0.36
    Aqua
    0.36
    opat
    0.35
    Offline
    0.35
    axe
    0.35
    Hover
    0.35
    intervention
    0.35
    Activations Density 0.000%

    No Known Activations