© 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. 199619
    Prev
    Next
    INDEX
    Explanations

    electricity

    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
     электро
    1.80
     Elec
    1.70
    电
    1.66
     elektr
    1.64
    Elekt
    1.64
     الکتر
    1.63
    Ele
    1.62
     elec
    1.62
     електро
    1.59
    電
    1.59
    POSITIVE LOGITS
    Landing
    0.35
     Inf
    0.34
    CacheV
    0.34
    蟳
    0.34
    াঁ
    0.34
     Play
    0.34
     Kern
    0.34
     गर्भ
    0.34
     अग
    0.33
    ismer
    0.33
    Activations Density 0.008%

    No Known Activations