© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247315
    Prev
    Next
    INDEX
    Explanations

    motorcycle displacement and engine size

    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_40_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
     Pi
    0.40
    Pi
    0.38
    馋
    0.36
     pariy
    0.36
     كلام
    0.35
     asphalt
    0.35
    cv
    0.35
    bolt
    0.35
    BOL
    0.34
     ///<
    0.34
    POSITIVE LOGITS
     казіно
    0.40
    世話
    0.40
     Ormond
    0.38
    临
    0.38
     урока
    0.37
    ộn
    0.37
    ვნ
    0.35
     фотографии
    0.35
     serialization
    0.35
    autoref
    0.35
    Activations Density 0.002%

    No Known Activations