© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100408
    Prev
    Next
    INDEX
    Explanations

    roux, frame, Nationalist

    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_16_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
     философ
    0.55
     Мар
    0.52
     философии
    0.50
    Мар
    0.48
     Schlag
    0.47
     Ó
    0.46
     Áng
    0.46
     Türk
    0.46
     irre
    0.45
     څنګه
    0.45
    POSITIVE LOGITS
    话
    0.52
    排
    0.48
    DOM
    0.46
    Browser
    0.46
    Outgoing
    0.46
     작동
    0.46
    Geocoder
    0.46
    those
    0.45
    电信
    0.44
    iosk
    0.43
    Activations Density 0.000%

    No Known Activations