© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77709
    Prev
    Next
    INDEX
    Explanations

    K

    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_53_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
    INDE
    0.39
    пенди
    0.39
    substr
    0.38
    regs
    0.38
    CreateParams
    0.37
    漓
    0.37
    usz
    0.36
    urved
    0.36
     PEAR
    0.36
    还有
    0.36
    POSITIVE LOGITS
     Nij
    0.41
     സി
    0.39
    និ
    0.38
    菻
    0.38
     Robbie
    0.37
     Nikola
    0.37
     Wool
    0.37
     Valuation
    0.37
    ว
    0.37
     Tp
    0.36
    Activations Density 0.001%

    No Known Activations