© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 143024
    Prev
    Next
    INDEX
    Explanations

    taking out trash

    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
    Not in Any Lists

    No Comments

    Negative Logits
     bin
    0.43
     large
    0.41
     NuGet
    0.39
     Bin
    0.39
    爣
    0.39
    Utility
    0.38
     Прав
    0.38
     hii
    0.38
    Nu
    0.37
     tenu
    0.37
    POSITIVE LOGITS
    ^{[\
    0.41
    コード
    0.39
    ષ્ય
    0.39
    APDS
    0.38
    lceil
    0.37
     detrás
    0.36
    dock
    0.36
    üssel
    0.36
     Cocker
    0.36
     карбо
    0.36
    Activations Density 0.002%

    No Known Activations