© 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. 133368
    Prev
    Next
    INDEX
    Explanations

    addresses

    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
     Middleware
    0.48
     L
    0.42
     সাব
    0.40
     tailles
    0.40
     tin
    0.39
     зал
    0.39
     sab
    0.38
     devol
    0.38
    艘
    0.38
     len
    0.38
    POSITIVE LOGITS
    ικ
    0.39
     جوسینو
    0.38
    JComboBox
    0.38
    HCO
    0.38
    强化
    0.37
    िज्या
    0.37
    BSC
    0.37
     Maced
    0.37
    BET
    0.37
    Simulator
    0.36
    Activations Density 0.000%

    No Known Activations