© 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. 130113
    Prev
    Next
    INDEX
    Explanations

    tribes regions peoples

    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
     F
    0.45
    F
    0.40
    .]+
    0.38
     Fib
    0.38
    Fib
    0.36
    arde
    0.36
    ARDO
    0.36
     Silica
    0.35
    <unused52>
    0.35
    ables
    0.35
    POSITIVE LOGITS
     Lucien
    0.42
     мероприятий
    0.41
    دس
    0.41
     crossword
    0.41
     paradigm
    0.39
     paradigms
    0.38
     aparelho
    0.37
     hok
    0.37
     gatherings
    0.36
    Lug
    0.36
    Activations Density 0.001%

    No Known Activations