© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34680
    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
     dur
    0.48
    dur
    0.46
     sol
    0.44
    ソル
    0.43
    arf
    0.42
     dürfen
    0.42
    уч
    0.40
    僵
    0.40
    dür
    0.40
     Dur
    0.39
    POSITIVE LOGITS
    geb
    1.13
     Geb
    1.05
     geb
    1.03
    Geb
    0.99
     Give
    0.72
    give
    0.72
    Give
    0.70
     giving
    0.70
     give
    0.69
    giving
    0.66
    Activations Density 0.013%

    No Known Activations