© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146249
    Prev
    Next
    INDEX
    Explanations

    angles or punctuation

    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_0_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
    1.00
     a
    0.94
    大
    0.73
     to
    0.70
     be
    0.66
     it
    0.64
    ب
    0.64
    lis
    0.63
    browser
    0.62
    他的
    0.62
    POSITIVE LOGITS
     وړاندوینه
    0.64
    ເຮັດ
    0.61
    :
    0.59
    ᱗
    0.58
     ditth
    0.56
    ↵
    0.54
     футболдук
    0.54
    ᱐
    0.54
    Apakah
    0.51
    ે
    0.51
    Activations Density 0.000%

    No Known Activations