© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20380
    Prev
    Next
    INDEX
    Explanations

    ми / mi

    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_56_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
    м
    1.31
    om
    1.29
    OM
    1.04
    ám
    1.01
    ом
    0.93
    م
    0.88
    óm
    0.83
    وم
    0.79
    ам
    0.79
    öm
    0.78
    POSITIVE LOGITS
    ми
    0.57
    МИ
    0.55
     MI
    0.50
    mi
    0.49
    MI
    0.47
    メラ
    0.45
    ECH
    0.43
    می
    0.42
    kami
    0.40
    mib
    0.40
    Activations Density 0.003%

    No Known Activations