© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 41193
    Prev
    Next
    INDEX
    Explanations

    "से" followed by verbs/nouns

    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_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <0x0D>
    0.82
     to
    0.71
    </h2>
    0.66
    d
    0.61
    '
    0.58
     sta
    0.57
    ना
    0.56
     for
    0.56
    ва
    0.55
     erreichte
    0.55
    POSITIVE LOGITS
    ಜ್ಜ
    0.59
    arlı
    0.57
     핵심
    0.56
    ಷ್ಠ
    0.56
    pered
    0.55
     혁
    0.55
    arsipkan
    0.54
    शीर
    0.54
    Qnt
    0.54
    ಂಥ
    0.53
    Activations Density 0.000%

    No Known Activations