© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 159126
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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_50_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
    اليه
    0.40
    Salary
    0.39
    莪
    0.39
    Gaussian
    0.38
     keres
    0.38
    jaan
    0.38
    聚
    0.37
    孭
    0.37
     يه
    0.36
     القض
    0.36
    POSITIVE LOGITS
     controllability
    0.38
     oftentimes
    0.38
    ূর্ণ
    0.37
     ماند
    0.36
    yata
    0.36
     Legendary
    0.36
     transmissions
    0.36
    тая
    0.35
     Rica
    0.35
     ся
    0.35
    Activations Density 0.000%

    No Known Activations