© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 214086
    Prev
    Next
    INDEX
    Explanations

    countries

    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_43_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
     supra
    0.45
    leg
    0.40
     izdel
    0.39
    undas
    0.39
    legi
    0.38
     Spreadsheet
    0.38
    thar
    0.38
    <s>
    0.38
    onant
    0.37
    LEG
    0.36
    POSITIVE LOGITS
    දය
    0.38
    博物馆
    0.38
     extrémités
    0.37
    Mans
    0.37
     Mans
    0.36
     ದೇಹ
    0.36
     Attitude
    0.36
     Flushing
    0.36
     provoked
    0.35
    िफिकेट
    0.35
    Activations Density 0.001%

    No Known Activations