© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40288
    Prev
    Next
    INDEX
    Explanations

    overestimateornephew

    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
     infringing
    0.56
     gaz
    0.53
     problematic
    0.51
     издели
    0.50
    弾
    0.49
     glaring
    0.49
     elastic
    0.48
     gazebo
    0.48
     desiring
    0.47
     patios
    0.47
    POSITIVE LOGITS
    er
    0.56
    ر
    0.55
    u
    0.54
    ن
    0.52
    R
    0.50
     Grocery
    0.50
     Nutrition
    0.49
     Ass
    0.49
    ﺮ
    0.49
    ad
    0.49
    Activations Density 0.000%

    No Known Activations