© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213684
    Prev
    Next
    INDEX
    Explanations

    assembly language

    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_50_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
    raction
    0.39
    gh
    0.38
    inz
    0.38
     Wilhelm
    0.38
    ாலும்
    0.37
    GB
    0.37
    ARY
    0.37
    g
    0.37
    AL
    0.37
    gb
    0.37
    POSITIVE LOGITS
    ক্সি
    0.46
    MX
    0.41
    CDATA
    0.41
    deposit
    0.38
     Ники
    0.38
     Minh
    0.37
     Cyprus
    0.36
    Ẫ
    0.36
     Maltese
    0.36
    ompact
    0.36
    Activations Density 0.005%

    No Known Activations