© 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. 131080
    Prev
    Next
    INDEX
    Explanations

    places locations travel

    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
     impurities
    0.46
    ⠊
    0.43
     Ser
    0.40
    Ser
    0.40
     ym
    0.40
     اشت
    0.39
     spat
    0.38
    achat
    0.38
    astung
    0.38
    ast
    0.37
    POSITIVE LOGITS
    kel
    0.47
    KEL
    0.47
     মে
    0.46
    坂
    0.46
     kel
    0.45
     кел
    0.43
    くら
    0.42
     Shak
    0.40
     Zak
    0.40
    খ্যা
    0.39
    Activations Density 0.009%

    No Known Activations