© 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. 38693
    Prev
    Next
    INDEX
    Explanations

    kitchen-aid, KiCad, kitchen towel, kitchen witch, Bok Joo

    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
    на
    0.91
    3
    0.80
    ের
    0.80
    2
    0.80
    nu
    0.79
    6
    0.78
    ne
    0.74
    7
    0.74
    ים
    0.74
    8
    0.71
    POSITIVE LOGITS
    ol
    0.73
    ്യ
    0.67
    ij
    0.66
    "};
    0.65
    cribable
    0.63
    Trap
    0.61
     retrouvé
    0.61
     prennent
    0.60
    ");
    0.60
    -”
    0.60
    Activations Density 0.016%

    No Known Activations