© 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. 38876
    Prev
    Next
    INDEX
    Explanations

    windshield / central / slope

    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
    ;
    0.78
     карь
    0.77
    ir
    0.72
    j
    0.72
    ad
    0.70
    𝟬
    0.69
     as
    0.68
    <h1>
    0.68
    +
    0.66
     españ
    0.66
    POSITIVE LOGITS
    ιβ
    0.63
    8
    0.59
    йы
    0.57
    دا
    0.56
    ival
    0.55
    ార్
    0.55
    <0xB9>
    0.54
    στη
    0.54
    S
    0.54
    رات
    0.54
    Activations Density 0.000%

    No Known Activations