© 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. 46533
    Prev
    Next
    INDEX
    Explanations

    surface 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_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
     civilized
    0.64
     τ
    0.60
     στα
    0.60
     προσ
    0.57
     κα
    0.57
     fiable
    0.57
     derivation
    0.57
     congru
    0.56
     converg
    0.56
    で行
    0.55
    POSITIVE LOGITS
    on
    0.69
    ()=>{
    0.69
     Mün
    0.68
    4
    0.66
    ৫
    0.64
    nič
    0.63
    ž
    0.62
    ки
    0.61
    ż
    0.60
    ك
    0.59
    Activations Density 0.004%

    No Known Activations