© 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. 215035
    Prev
    Next
    INDEX
    Explanations

    Sagrada, Gaudi

    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
    關
    0.43
    守
    0.42
     cổng
    0.41
    ronectin
    0.40
    关
    0.40
    Bluetooth
    0.39
    bluetooth
    0.38
    重心
    0.38
     rehabilitate
    0.37
     Bluetooth
    0.36
    POSITIVE LOGITS
    aske
    0.44
    Hir
    0.40
    <{
    0.38
    zustellen
    0.38
    υνα
    0.37
     Estelle
    0.37
    aries
    0.37
     Hir
    0.37
    ยา
    0.37
    IONAL
    0.37
    Activations Density 0.000%

    No Known Activations