© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137328
    Prev
    Next
    INDEX
    Explanations

    muscle tension

    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_12_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
    l
    0.63
    t
    0.49
    OL
    0.48
    Cafe
    0.44
    ac
    0.44
    的区别
    0.43
    分享
    0.43
     tension
    0.43
     demarcation
    0.43
    ㅜ
    0.43
    POSITIVE LOGITS
     Machado
    0.51
     perpetrated
    0.50
     оде
    0.49
     iPod
    0.47
    锒
    0.47
    enan
    0.46
     Analyst
    0.45
    <unused988>
    0.45
     اندر
    0.44
    <unused2027>
    0.44
    Activations Density 0.003%

    No Known Activations