© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195312
    Prev
    Next
    INDEX
    Explanations

    places and architecture

    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
    যায়
    0.44
     toug
    0.42
    玻
    0.40
    아야
    0.39
     Alan
    0.39
    ウター
    0.38
    Alan
    0.38
    laan
    0.38
    Algo
    0.38
    燎
    0.38
    POSITIVE LOGITS
    BTC
    0.40
     Ramb
    0.39
    тельство
    0.38
     มิถุนายน
    0.38
    ệm
    0.36
    ম্ব
    0.35
    Спа
    0.35
    urk
    0.35
     plasmas
    0.34
    Bit
    0.34
    Activations Density 0.003%

    No Known Activations