© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46962
    Prev
    Next
    INDEX
    Explanations

    is ... this

    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_10_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
    ی
    1.06
     are
    0.80
    irani
    0.77
    desired
    0.73
     the
    0.71
    ים
    0.71
    classroom
    0.71
    nodo
    0.70
    are
    0.70
    ir
    0.69
    POSITIVE LOGITS
    ع
    0.66
    其他
    0.66
    נ
    0.66
    掸
    0.63
    小
    0.62
    ри
    0.62
    h
    0.61
    人的
    0.60
    اب
    0.59
    的技术
    0.59
    Activations Density 0.024%

    No Known Activations