© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116113
    Prev
    Next
    INDEX
    Explanations

    body css styling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     HARR
    0.38
     Cunningham
    0.36
     TEA
    0.36
     அணி
    0.34
     підпри
    0.34
     Pigs
    0.33
     Serviços
    0.33
    탤
    0.33
     Harrison
    0.32
    ARK
    0.32
    POSITIVE LOGITS
     radix
    0.39
    ेटिव
    0.39
    勾
    0.39
    álně
    0.38
     mods
    0.38
     ater
    0.37
    复杂度
    0.36
    }{$\
    0.36
     размеры
    0.36
     shock
    0.35
    Activations Density 0.001%

    No Known Activations