© 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
    2. Gemma-3-27B-IT
    3. 51-GEMMASCOPE-2-TRANSCODER-262K
    4. 68362
    Prev
    Next
    INDEX
    Explanations

    abbreviations and codes

    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
     пет
    0.40
    ޑ
    0.38
     EL
    0.38
     حسن
    0.38
     Ignatius
    0.38
     Cove
    0.38
     Donna
    0.37
    =('
    0.37
     discour
    0.37
     ven
    0.37
    POSITIVE LOGITS
    koe
    0.42
     moisturizer
    0.39
     PSA
    0.39
     koa
    0.38
    Jar
    0.38
    PSA
    0.38
    彗
    0.38
    forEach
    0.38
    kowania
    0.38
    TryGetValue
    0.37
    Activations Density 0.000%

    No Known Activations