© 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. 41750
    Prev
    Next
    INDEX
    Explanations

    armament, arm, control, sales, negotiations

    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
    6
    0.73
    ↵
    0.72
    9
    0.66
    5
    0.65
    ر
    0.64
     to
    0.63
    টি
    0.63
    মনসিংহ
    0.61
     Armen
    0.60
    ,
    0.60
    POSITIVE LOGITS
    k
    0.74
    c
    0.72
     và
    0.70
     dará
    0.70
     của
    0.67
    <0x80>
    0.65
    ૧
    0.65
     ແລະ
    0.64
     a
    0.63
    ຂອງ
    0.63
    Activations Density 0.007%

    No Known Activations