© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 250960
    Prev
    Next
    INDEX
    Explanations

    pe

    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_56_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
     パ
    0.41
     ಪಾ
    0.38
    entliche
    0.38
     પા
    0.37
    傗
    0.37
    ﾊ
    0.37
    ഷ്ണ
    0.36
    ólicas
    0.35
    emaakt
    0.35
    tze
    0.35
    POSITIVE LOGITS
     пе
    2.30
     Пе
    2.13
    ペ
    2.11
     pé
    2.06
     Pé
    1.98
    Пе
    1.94
     PE
    1.93
     Pek
    1.93
     페
    1.91
     PEC
    1.87
    Activations Density 0.014%

    No Known Activations