© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13338
    Prev
    Next
    INDEX
    Explanations

    polynomial ring

    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_40_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
    णार
    0.42
     récip
    0.38
     cuerpo
    0.38
     Transplantation
    0.38
    ຊ
    0.38
     incurable
    0.37
     diaspora
    0.36
     Kanban
    0.36
     przypad
    0.36
     جواب
    0.36
    POSITIVE LOGITS
    emons
    0.39
     coatings
    0.38
    টেড
    0.38
     ^=
    0.38
    كام
    0.38
     graded
    0.37
     régulière
    0.37
     Mim
    0.37
     regular
    0.37
    ussed
    0.37
    Activations Density 0.004%

    No Known Activations