© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 47962
    Prev
    Next
    INDEX
    Explanations

    kai

    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
    t
    0.88
    و
    0.84
    í
    0.83
    И
    0.79
    সময়
    0.71
    ي
    0.70
    ı
    0.68
    ли
    0.67
    را
    0.67
    ｫ
    0.66
    POSITIVE LOGITS
     hidrógeno
    0.68
    ᱕
    0.66
    aría
    0.65
     greater
    0.64
    ール
    0.64
    9
    0.64
    ться
    0.63
    ᱗
    0.62
     unbeatable
    0.62
     tableware
    0.62
    Activations Density 0.000%

    No Known Activations