© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79794
    Prev
    Next
    INDEX
    Explanations

    calculating sum of numbers

    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_31_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
     सहानुभूति
    0.38
    決定
    0.38
     ခု
    0.38
    BoardManager
    0.38
     बीन
    0.37
    ͎
    0.37
     Wow
    0.37
    搏
    0.37
     웃
    0.36
     پسند
    0.36
    POSITIVE LOGITS
    licka
    0.43
     descendants
    0.39
     sum
    0.38
     summa
    0.37
     coax
    0.36
    sum
    0.36
     descendant
    0.36
     meant
    0.35
     shedding
    0.35
     sums
    0.34
    Activations Density 0.010%

    No Known Activations