© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 68533
    Prev
    Next
    INDEX
    Explanations

    Charles / Charlie

    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_51_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
    preload
    0.45
    lund
    0.42
     Santi
    0.41
     Santiago
    0.40
     مخاط
    0.40
    kel
    0.39
    Loader
    0.39
    僧
    0.39
    Los
    0.39
     Leung
    0.39
    POSITIVE LOGITS
    DanhMucSP
    0.43
    鸨
    0.40
    क्सीडेंट
    0.39
    Բ
    0.38
     MM
    0.37
     डेविड
    0.36
     ম্যানে
    0.36
     ডিগ্রি
    0.34
    necks
    0.34
     billowing
    0.34
    Activations Density 0.001%

    No Known Activations