© 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. 157027
    Prev
    Next
    INDEX
    Explanations

    can

    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
    亠
    0.41
    ilayer
    0.38
    kový
    0.38
     teleport
    0.38
     Показа
    0.37
     avrà
    0.37
    ИА
    0.36
    pointB
    0.35
    ঙ্গিক
    0.35
     acclimat
    0.35
    POSITIVE LOGITS
    '
    0.59
    ’
    0.57
     novas
    0.41
    usable
    0.40
    safe
    0.40
    ＇
    0.39
     unattended
    0.38
     nuevas
    0.38
     bilden
    0.38
    &#
    0.38
    Activations Density 0.003%

    No Known Activations