© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45298
    Prev
    Next
    INDEX
    Explanations

    kinematics and linkages

    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_10_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
    ad
    0.88
    ↵
    0.78
    ；
    0.76
    t
    0.72
    <0x80>
    0.68
    i
    0.67
    am
    0.63
    de
    0.62
    wa
    0.61
    as
    0.60
    POSITIVE LOGITS
     multiplications
    0.70
    ж
    0.69
    룺
    0.68
     cranks
    0.68
     multiplies
    0.67
    М
    0.66
    Т
    0.65
     другим
    0.65
    েনের
    0.64
     orchestras
    0.64
    Activations Density 0.014%

    No Known Activations