© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31462
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ╝
    0.41
     towers
    0.40
     каб
    0.38
     Towers
    0.37
    ahu
    0.37
    天赋
    0.36
     tower
    0.36
    alne
    0.36
    yet
    0.36
    aruhi
    0.35
    POSITIVE LOGITS
    enaries
    0.41
    겼
    0.39
    subseteq
    0.39
    Ґ
    0.38
     वेळा
    0.37
    GES
    0.36
     practitioner
    0.36
    Georg
    0.36
     অসম
    0.36
    Mutual
    0.35
    Activations Density 0.001%

    No Known Activations