© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74882
    Prev
    Next
    INDEX
    Explanations

    attracts visitors and tourists

    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_31_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
    ੱਸ
    0.43
     tours
    0.42
     टूर
    0.41
    distances
    0.39
    dozen
    0.38
    tour
    0.38
     tour
    0.38
    ໌
    0.37
     TOUR
    0.36
     аэро
    0.36
    POSITIVE LOGITS
     作業
    0.44
     //[
    0.39
    ]];
    0.38
     食品
    0.38
     bảng
    0.38
     akzept
    0.38
     직
    0.37
     Psychiatry
    0.37
     Blog
    0.37
    位数
    0.37
    Activations Density 0.005%

    No Known Activations