© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85793
    Prev
    Next
    INDEX
    Explanations

    Area Network spectrum

    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_3_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
    嫨
    0.67
     ಅವಕಾಶ
    0.66
     SoaException
    0.66
    ಬ್ಬಿಣ
    0.64
    mprj
    0.63
    beqz
    0.63
    笂
    0.63
    ेलकम
    0.62
    棿
    0.61
    prf
    0.60
    POSITIVE LOGITS
     to
    1.05
    지
    1.00
     that
    0.96
     for
    0.95
    an
    0.92
    ut
    0.90
    าย
    0.89
    ט
    0.86
    on
    0.85
    ।
    0.85
    Activations Density 0.014%

    No Known Activations