© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242630
    Prev
    Next
    INDEX
    Explanations

    axiomatic systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    مال
    0.37
     abys
    0.37
     اللہ
    0.36
    Schools
    0.36
     scuole
    0.36
    畄
    0.36
    ंबा
    0.35
    蟠
    0.35
     schools
    0.35
     blacksmith
    0.35
    POSITIVE LOGITS
    system
    0.66
     system
    0.63
     sistema
    0.59
     نظام
    0.57
     systemu
    0.55
     системой
    0.54
    系统
    0.53
     systeem
    0.53
     시스템
    0.52
     系统
    0.52
    Activations Density 0.002%

    No Known Activations