© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29319
    Prev
    Next
    INDEX
    Explanations

    carbon footprint

    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
     reconnaît
    0.59
    [
    0.59
    کور
    0.57
     revolve
    0.57
    с
    0.55
     schist
    0.54
    ໃຈ
    0.54
    p
    0.54
    iterate
    0.54
    HEMAT
    0.53
    POSITIVE LOGITS
    اد
    0.72
    اش
    0.63
    ی
    0.61
     لقد
    0.60
    一丝
    0.58
    та
    0.56
    ě
    0.55
    ים
    0.54
     ад
    0.53
    O
    0.53
    Activations Density 0.001%

    No Known Activations