© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253958
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    -
    0.52
    times
    0.40
     اوقات
    0.39
     passada
    0.38
    TIMES
    0.38
     ليك
    0.37
    
    0.35
    низ
    0.35
    Tinh
    0.35
    ায়ের
    0.35
    POSITIVE LOGITS
     pan
    0.46
     পঞ্চ
    0.40
     u
    0.39
     pressing
    0.39
    讹
    0.38
     quoting
    0.38
     chest
    0.38
     shoulder
    0.37
    ,--
    0.36
    ohama
    0.34
    Activations Density 0.001%

    No Known Activations