© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 153377
    Prev
    Next
    INDEX
    Explanations

    non-Latin characters

    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_60_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
    i
    0.80
    u
    0.63
    at
    0.55
    all
    0.54
    ana
    0.48
     Cons
    0.46
    al
    0.46
     Cr
    0.46
    an
    0.45
    ate
    0.45
    POSITIVE LOGITS
    ش
    0.67
    Як
    0.66
    Мі
    0.65
    Під
    0.64
    Від
    0.63
    Якщо
    0.62
    ଶ
    0.61
    Vous
    0.60
    Пі
    0.60
    Ін
    0.60
    Activations Density 0.002%

    No Known Activations