© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39761
    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_11_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
     of
    0.57
    ：
    0.55
     nons
    0.53
     be
    0.53
    自
    0.53
    ள்
    0.51
    ึ
    0.50
    笛
    0.50
    ūsų
    0.50
     on
    0.50
    POSITIVE LOGITS
     ayudar
    0.63
    that
    0.57
    ου
    0.56
     যাতে
    0.56
    تالي
    0.56
     imati
    0.55
    торое
    0.55
    imde
    0.54
     naprav
    0.53
    תה
    0.53
    Activations Density 0.000%

    No Known Activations