© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88047
    Prev
    Next
    INDEX
    Explanations

    white phosphorus and sunlight

    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
    ส
    0.68
    с
    0.67
     to
    0.65
    ۹
    0.64
    س
    0.60
    ز
    0.60
    ీ
    0.60
    نا
    0.59
    estamp
    0.59
    ス
    0.58
    POSITIVE LOGITS
    u
    0.76
    n
    0.75
     rimane
    0.73
     پیسې
    0.71
    d
    0.70
    ת
    0.68
     deset
    0.66
    0.63
     podpor
    0.61
     temel
    0.61
    Activations Density 0.002%

    No Known Activations