© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82078
    Prev
    Next
    INDEX
    Explanations

    _

    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_53_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
    III
    0.54
     III
    0.45
    (||
    0.44
    тку
    0.41
    Telefono
    0.38
    ޟ
    0.38
     Kak
    0.38
    ắn
    0.37
    )||
    0.37
    дак
    0.36
    POSITIVE LOGITS
    ছোট
    0.39
    úrate
    0.39
    જો
    0.38
    usnya
    0.38
     dưỡng
    0.37
     ich
    0.37
     အရ
    0.37
    ിക്കാം
    0.36
    澆
    0.36
     ker
    0.35
    Activations Density 0.001%

    No Known Activations