© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 198232
    Prev
    Next
    INDEX
    Explanations

    whiteboard / boards

    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_12_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
    J
    0.69
    Z
    0.62
    Charl
    0.61
    Samsung
    0.61
    Jose
    0.59
    Ze
    0.59
    Born
    0.59
    Lake
    0.59
    Teacher
    0.59
    VISA
    0.59
    POSITIVE LOGITS
     şark
    0.53
    壓縮
    0.52
    matory
    0.52
    
    0.48
    ાઇ
    0.48
    า
    0.47
     hàm
    0.47
     '</
    0.46
    ₆
    0.46
    ounds
    0.45
    Activations Density 0.000%

    No Known Activations