© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34000
    Prev
    Next
    INDEX
    Explanations

    code and programming

    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
     piu
    0.52
    ﾚ
    0.50
     Dont
    0.50
     حاجه
    0.48
     นํา
    0.48
     مساله
    0.46
     คํา
    0.46
    Dont
    0.45
    ो
    0.45
     ทํา
    0.44
    POSITIVE LOGITS
    ঙ্কার
    0.42
    пропетров
    0.39
    ওয়ায়
    0.38
    halla
    0.37
     EdgeInsets
    0.37
    躯
    0.36
    KYO
    0.36
     über
    0.36
    OutputStream
    0.36
    hann
    0.35
    Activations Density 0.000%

    No Known Activations