© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52071
    Prev
    Next
    INDEX
    Explanations

    change or comparison

    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_55_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
     <<"
    0.40
     स्टार्टिंग
    0.37
    startsWith
    0.35
     حمایت
    0.35
    Ợ
    0.35
    agul
    0.35
    oreau
    0.34
    uncan
    0.34
    icare
    0.34
    椏
    0.34
    POSITIVE LOGITS
     altered
    0.67
     bigger
    0.64
     faster
    0.63
     different
    0.62
     changed
    0.62
     farklı
    0.62
     expensive
    0.60
     thinner
    0.59
     enhanced
    0.59
     diferentes
    0.59
    Activations Density 0.006%

    No Known Activations