© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31853
    Prev
    Next
    INDEX
    Explanations

    years in 5 or 10

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     taped
    0.38
     clairement
    0.38
     poached
    0.37
     clearly
    0.37
     情
    0.37
    clearly
    0.37
     dạng
    0.36
     الفترة
    0.35
     Clearly
    0.35
    শ্যক
    0.35
    POSITIVE LOGITS
    ayena
    0.47
    ኘ
    0.41
    apayati
    0.39
     urządzenia
    0.39
     esper
    0.39
    ቃ
    0.38
    ymi
    0.38
    steiger
    0.38
     hundred
    0.37
    ന്നി
    0.37
    Activations Density 0.003%

    No Known Activations