© 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. 225066
    Prev
    Next
    INDEX
    Explanations

    Russian words, specific place names

    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
    弑
    0.63
     отвеча
    0.60
     ဂ
    0.60
    ၀၀
    0.59
     மெட்ரோ
    0.58
    тта
    0.58
     कारकों
    0.57
     сколько
    0.57
     chattel
    0.57
     демо
    0.56
    POSITIVE LOGITS
    '
    0.76
    t
    0.70
    in
    0.70
    to
    0.68
    su
    0.66
    ua
    0.64
     at
    0.63
    ren
    0.61
    sa
    0.61
    ru
    0.60
    Activations Density 0.000%

    No Known Activations