© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89053
    Prev
    Next
    INDEX
    Explanations

    King Crimson, B.B. King Museum, kingly

    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
    ند
    0.68
    تح
    0.62
    কি
    0.60
    ط
    0.59
    لک
    0.57
    체
    0.57
    مل
    0.56
    لان
    0.56
    constraintStart
    0.55
    мони
    0.55
    POSITIVE LOGITS
    o
    1.05
     s
    0.89
     i
    0.88
     a
    0.77
     l
    0.75
     no
    0.69
    ii
    0.68
    (
    0.68
    s
    0.67
     f
    0.66
    Activations Density 0.001%

    No Known Activations