© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192350
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by objects or actions

    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_4_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
    '
    0.73
    <0xA5>
    0.67
     have
    0.66
    માં
    0.65
    )
    0.65
    <0x80>
    0.63
    ang
    0.62
    ária
    0.61
    have
    0.61
    ೀ
    0.61
    POSITIVE LOGITS
     INumber
    0.72
    스
    0.66
    e
    0.63
    ChooseServer
    0.63
     Tài
    0.61
    ﺭ
    0.60
    GeV
    0.60
    NU
    0.59
    و
    0.59
     Tempat
    0.58
    Activations Density 0.223%

    No Known Activations