© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57299
    Prev
    Next
    INDEX
    Explanations

    Monte

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    idcoin
    0.48
    dien
    0.44
     spezial
    0.40
    棸
    0.38
    decin
    0.37
    לות
    0.36
    riez
    0.36
     tige
    0.36
    lomer
    0.35
    ávez
    0.35
    POSITIVE LOGITS
     Redist
    0.46
    ceo
    0.43
    agle
    0.38
     未
    0.38
    video
    0.38
     Ultim
    0.37
     Manip
    0.37
    king
    0.37
    馴
    0.37
    athy
    0.36
    Activations Density 0.000%

    No Known Activations