© 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. 43394
    Prev
    Next
    INDEX
    Explanations

    al-zahara / zahra

    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
    ’
    0.78
     arka
    0.76
     not
    0.76
     ks
    0.68
     as
    0.67
     jogo
    0.67
     aras
    0.65
     irá
    0.64
    我们
    0.64
     reorgan
    0.64
    POSITIVE LOGITS
    ла
    1.03
    ?
    0.88
    the
    0.85
    !
    0.77
    ール
    0.75
    на
    0.75
    ला
    0.74
    an
    0.72
    ры
    0.68
    се
    0.68
    Activations Density 0.002%

    No Known Activations