© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89062
    Prev
    Next
    INDEX
    Explanations

    spectroscopy / spectrum analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    ação
    0.79
    ной
    0.64
    ération
    0.63
    ł
    0.63
    ită
    0.61
     곳
    0.61
    of
    0.58
     rte
    0.57
    ed
    0.57
     έ
    0.57
    POSITIVE LOGITS
    د
    0.88
    ب
    0.81
    м
    0.80
    م
    0.80
    ي
    0.80
    N
    0.76
    ت
    0.75
    ر
    0.74
    dnn
    0.73
    حظ
    0.73
    Activations Density 0.000%

    No Known Activations