© 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. 35072
    Prev
    Next
    INDEX
    Explanations

    Perth

    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
     immune
    0.38
    лии
    0.37
    浲
    0.37
     sét
    0.36
     врача
    0.36
    ಚ
    0.36
    BinaryOperation
    0.35
    心情
    0.35
    咉
    0.35
     Swan
    0.35
    POSITIVE LOGITS
     PER
    0.71
    PER
    0.62
     Per
    0.55
    Per
    0.54
    Пер
    0.51
     퍼
    0.51
    Boulder
    0.51
    퍼
    0.50
     Perth
    0.49
     pér
    0.48
    Activations Density 0.002%

    No Known Activations