© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132941
    Prev
    Next
    INDEX
    Explanations

    plasma cell, volume, protein, lipid

    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_6_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
    ↵
    1.16
    '
    0.96
     to
    0.95
    h
    0.92
    6
    0.92
    </strong>
    0.89
     année
    0.86
     employé
    0.85
     années
    0.82
    REN
    0.82
    POSITIVE LOGITS
    is
    1.19
    ین
    1.03
    in
    1.02
     pensado
    0.98
    ز
    0.93
     می‌شود
    0.88
    ر
    0.86
    ять
    0.85
    ங்க
    0.84
    ید
    0.84
    Activations Density 0.000%

    No Known Activations