© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196977
    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_46_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
    尖
    0.39
     painting
    0.37
    owana
    0.37
    GetComponent
    0.35
     component
    0.35
    柒
    0.35
    บาย
    0.35
    zeichnet
    0.35
     Vand
    0.35
    七
    0.35
    POSITIVE LOGITS
     бонус
    0.41
     Duitse
    0.41
     italiana
    0.41
     RADIATION
    0.41
     Radi
    0.40
     aplicada
    0.40
    结算
    0.40
    德国
    0.40
     написать
    0.40
     यादगार
    0.40
    Activations Density 0.000%

    No Known Activations