© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123085
    Prev
    Next
    INDEX
    Explanations

    high end game products

    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_3_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
    ються
    0.79
     è
    0.75
     הוא
    0.70
     הם
    0.70
     are
    0.69
     حتی
    0.68
     đều
    0.67
     janë
    0.67
     بندی
    0.63
     ทำให้
    0.62
    POSITIVE LOGITS
    ت
    1.15
    t
    0.97
    تس
    0.84
    c
    0.82
    تالي
    0.81
    ون
    0.79
    ac
    0.77
    in
    0.76
    ת
    0.76
    ن
    0.76
    Activations Density 0.002%

    No Known Activations