© 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. 31729
    Prev
    Next
    INDEX
    Explanations

    balloon string and air

    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_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
    SHO
    0.38
     bav
    0.37
    घ
    0.37
     bru
    0.36
    物品
    0.35
     nome
    0.35
     altar
    0.35
    ┏
    0.35
    ඳ
    0.34
     numer
    0.34
    POSITIVE LOGITS
    tempCard
    0.37
     polystyrene
    0.37
     Jullie
    0.36
    ounters
    0.36
     getDescription
    0.35
     Tripathi
    0.34
     સાર
    0.34
     disg
    0.34
     आण
    0.34
    ವೆ
    0.33
    Activations Density 0.038%

    No Known Activations