© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53623
    Prev
    Next
    INDEX
    Explanations

    appearance or form

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    的样子
    0.38
    เส้น
    0.37
     यही
    0.36
     เส้น
    0.36
     ક્ષ
    0.35
    ชน
    0.33
    を与える
    0.32
    巳
    0.32
    धारणा
    0.31
    宣言
    0.31
    POSITIVE LOGITS
     colored
    2.09
     shaped
    2.08
     coloured
    2.06
     flavored
    1.88
     flavoured
    1.88
    Colored
    1.83
     Shaped
    1.81
     sized
    1.77
     styled
    1.76
     Colored
    1.76
    Activations Density 0.274%

    No Known Activations