© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26878
    Prev
    Next
    INDEX
    Explanations

    smoothness and wrinkles

    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
     étaient
    0.54
    ק
    0.53
    </h2>
    0.52
     impuestos
    0.49
    นัก
    0.49
     évaluation
    0.49
     allemand
    0.48
    жив
    0.48
     etti
    0.47
     angolo
    0.47
    POSITIVE LOGITS
    <h4>
    0.66
    Smooth
    0.64
    و
    0.61
     smooth
    0.60
     can
    0.58
     blistering
    0.58
    ال
    0.57
    ل
    0.57
    ය
    0.56
    ويل
    0.56
    Activations Density 0.032%

    No Known Activations