© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143674
    Prev
    Next
    INDEX
    Explanations

    Fullmetal Alchemist

    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_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ParentObject
    0.40
     искать
    0.40
    itens
    0.40
    ุก
    0.39
    Consistency
    0.38
     ingresar
    0.38
    猞
    0.37
     Mes
    0.37
    vej
    0.37
     gitu
    0.37
    POSITIVE LOGITS
     Profess
    0.38
     آنا
    0.36
    Carol
    0.36
    Brett
    0.35
    ธรรมชาติ
    0.35
     সম
    0.35
    toLocale
    0.35
    box
    0.34
     باکس
    0.34
    葦
    0.34
    Activations Density 0.001%

    No Known Activations