© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194660
    Prev
    Next
    INDEX
    Explanations

    Kl

    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_50_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
    兰
    0.41
    恈
    0.41
    蘭
    0.41
    لان
    0.39
     Ам
    0.39
     ranch
    0.38
    خول
    0.38
     Ranch
    0.38
    㻴
    0.37
     Am
    0.37
    POSITIVE LOGITS
    kve
    0.39
    pes
    0.39
    elti
    0.39
    assie
    0.38
    vag
    0.38
    ucin
    0.38
    up
    0.38
    plaat
    0.37
    vali
    0.37
    abcdef
    0.37
    Activations Density 0.000%

    No Known Activations