© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87973
    Prev
    Next
    INDEX
    Explanations

    alpha blendingalpha channelalpha insights

    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
    pesar
    0.66
    cumin
    0.59
    мам
    0.59
    ါ
    0.57
    emiz
    0.57
     ພວກເຮົາ
    0.56
    dach
    0.55
    imageBase
    0.55
    다
    0.54
    stances
    0.53
    POSITIVE LOGITS
    ’
    0.70
    ");
    0.65
    ";
    0.64
    য়ের
    0.64
     הראש
    0.64
    ",
    0.61
    ント
    0.61
     ",
    0.60
    ">
    0.58
     svého
    0.58
    Activations Density 0.005%

    No Known Activations