© 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. 130955
    Prev
    Next
    INDEX
    Explanations

    abstract concepts

    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
    構
    0.85
    Gu
    0.64
     구
    0.63
    구
    0.60
    図
    0.60
     Gu
    0.57
    GU
    0.54
    Гу
    0.54
     GU
    0.54
     Гу
    0.53
    POSITIVE LOGITS
    ឡ
    0.38
     letter
    0.38
     zajedno
    0.37
    交
    0.37
     thr
    0.36
    VJ
    0.36
    шон
    0.35
    邙
    0.35
     pilot
    0.35
     debated
    0.35
    Activations Density 0.010%

    No Known Activations