© 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. 88911
    Prev
    Next
    INDEX
    Explanations

    function is called

    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
    Not in Any Lists

    No Comments

    Negative Logits
    头发
    0.57
    ളം
    0.56
     alimentaires
    0.53
    profitLoss
    0.52
    ၆
    0.52
    specifiedByURL
    0.51
     longitude
    0.51
     좋습니다
    0.50
     الغذ
    0.50
     이미지
    0.49
    POSITIVE LOGITS
    คุณ
    0.58
    ње
    0.56
    ية
    0.50
     de
    0.49
    </span>
    0.49
     you
    0.49
    izar
    0.49
    дна
    0.48
    ский
    0.47
    th
    0.47
    Activations Density 0.004%

    No Known Activations