© 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. 199843
    Prev
    Next
    INDEX
    Explanations

    give

    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
    τό
    0.41
    ঘু
    0.39
    íta
    0.39
    manes
    0.39
     sleeping
    0.38
    僄
    0.38
     Hind
    0.38
    лини
    0.37
    ôi
    0.37
    planar
    0.37
    POSITIVE LOGITS
     give
    0.56
    Give
    0.56
     Gives
    0.56
     gives
    0.55
    gives
    0.55
     Give
    0.54
     Giving
    0.51
    给
    0.49
    give
    0.49
     giving
    0.48
    Activations Density 0.001%

    No Known Activations