© 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. 247086
    Prev
    Next
    INDEX
    Explanations

    Quality Management Systems

    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
    学历
    0.44
    žití
    0.39
    ត្រូ
    0.36
    进口
    0.35
     confound
    0.34
     diagonally
    0.34
    ইহ
    0.34
    ე
    0.34
     quas
    0.33
     চ্যানে
    0.33
    POSITIVE LOGITS
    audience
    0.38
     автомоби
    0.36
     Bing
    0.35
     automóvil
    0.34
    خص
    0.34
    Bing
    0.34
     सरा
    0.33
    êng
    0.33
    brar
    0.33
    èi
    0.32
    Activations Density 0.003%

    No Known Activations