© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200405
    Prev
    Next
    INDEX
    Explanations

    names or introductions followed by clarification

    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_37_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
     your
    0.39
     kaz
    0.38
     obiekt
    0.38
    Your
    0.37
    ពេ
    0.35
    ――――
    0.35
    *{\
    0.35
    閣
    0.35
    Chocolate
    0.34
     kq
    0.34
    POSITIVE LOGITS
     Andy
    0.43
     Daniel
    0.40
     approximates
    0.40
    рованы
    0.40
     Timothy
    0.40
     tensions
    0.38
    ictured
    0.37
     الدكتور
    0.37
     مرحبا
    0.37
     María
    0.37
    Activations Density 0.003%

    No Known Activations