© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47095
    Prev
    Next
    INDEX
    Explanations

    fuse box

    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
     modelo
    0.73
     puede
    0.70
     riguarda
    0.70
     lubric
    0.68
     macho
    0.68
    a
    0.68
    i
    0.67
     humide
    0.66
     può
    0.65
     alimenta
    0.65
    POSITIVE LOGITS
    Fusion
    0.88
    fusion
    0.81
    Fuse
    0.80
    ur
    0.77
    Fus
    0.76
     fuses
    0.69
     fusion
    0.67
     Fusion
    0.67
    sl
    0.66
    (
    0.66
    Activations Density 0.003%

    No Known Activations