© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199047
    Prev
    Next
    INDEX
    Explanations

    expected

    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
    적
    0.44
    atically
    0.44
    ಿಸಿದ
    0.42
    atic
    0.38
    ']:
    0.38
    ing
    0.37
    matics
    0.37
     seleccionado
    0.36
    ల్‌
    0.36
    matically
    0.36
    POSITIVE LOGITS
     getNodeId
    0.40
    gü
    0.39
    hér
    0.38
     HAV
    0.37
    HAV
    0.36
     Boul
    0.36
     قوي
    0.36
    dym
    0.36
    杝
    0.35
    gb
    0.35
    Activations Density 0.001%

    No Known Activations