© 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. 77968
    Prev
    Next
    INDEX
    Explanations

    say step by step

    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
    tung
    0.41
    N
    0.41
    Πα
    0.40
     verst
    0.39
     N
    0.38
     Göl
    0.38
    ungk
    0.38
    Па
    0.37
    autos
    0.37
     Цу
    0.37
    POSITIVE LOGITS
    xAxis
    0.39
    legen
    0.37
     etat
    0.37
     具体
    0.37
     अधीनस्थों
    0.37
     而且
    0.37
    窖
    0.37
     بدي
    0.36
     علا
    0.36
     cfg
    0.36
    Activations Density 0.000%

    No Known Activations