© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30972
    Prev
    Next
    INDEX
    Explanations

    numpy array initialization

    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_7_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
     has
    1.10
     is
    1.05
     The
    1.05
    ри
    0.98
    ل
    0.98
    ки
    0.93
    on
    0.87
    od
    0.86
     were
    0.82
     had
    0.81
    POSITIVE LOGITS
    在
    0.82
    ۔
    0.79
    ري
    0.75
    ።
    0.75
    도
    0.74
    ও
    0.71
    في
    0.71
    V
    0.69
    もら
    0.68
    btnLogin
    0.63
    Activations Density 0.002%

    No Known Activations