© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 86939
    Prev
    Next
    INDEX
    Explanations

    SE, locker, lights, Soldier

    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
    un
    0.79
    ק
    0.71
    e
    0.71
    ીએ
    0.62
     internalized
    0.61
     negate
    0.60
    ak
    0.60
    ají
    0.59
     preclude
    0.58
     μπορεί
    0.57
    POSITIVE LOGITS
    که
    0.81
    )。
    0.79
    ll
    0.77
    )।
    0.74
    ۲
    0.72
    )!
    0.68
    یس
    0.68
    فی
    0.68
    )$.
    0.67
    $),
    0.66
    Activations Density 0.000%

    No Known Activations