© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45979
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_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
    lastname
    0.56
    cua
    0.54
    namefont
    0.51
     作品
    0.50
     UN
    0.49
     ता
    0.49
    𝐧
    0.49
     तक
    0.47
    tim
    0.47
     Zealand
    0.47
    POSITIVE LOGITS
     пациентов
    0.66
    ار
    0.60
    ق
    0.60
    Ꮕ
    0.58
    원
    0.55
    ل
    0.54
    दरअसल
    0.54
     заболеваний
    0.52
     американский
    0.52
    O
    0.52
    Activations Density 0.000%

    No Known Activations