© 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. 198002
    Prev
    Next
    INDEX
    Explanations

    art and technology

    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
    дзе
    0.43
    GAM
    0.41
     Scalar
    0.39
    गीय
    0.38
    嘉
    0.38
     кален
    0.38
     لوبو
    0.38
     peony
    0.38
     Jasmin
    0.38
    呠
    0.38
    POSITIVE LOGITS
    Tel
    0.50
    el
    0.46
    tel
    0.44
    телю
    0.44
    MainBinding
    0.42
    теля
    0.41
     Tel
    0.41
    atel
    0.41
    тельный
    0.41
    тель
    0.40
    Activations Density 0.024%

    No Known Activations