© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 182434
    Prev
    Next
    INDEX
    Explanations

    state machine state variables

    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_29_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
    urnama
    0.40
     unim
    0.39
    月份
    0.39
    substr
    0.38
     substr
    0.37
    曆
    0.36
    soever
    0.36
     assuntos
    0.36
     подели
    0.35
     mèo
    0.35
    POSITIVE LOGITS
     као
    0.39
    Ranking
    0.38
     invaluable
    0.38
     лучшие
    0.33
    丢
    0.33
     bankruptcy
    0.32
    グレード
    0.32
     Stick
    0.31
    yrı
    0.31
    𝗕
    0.31
    Activations Density 0.007%

    No Known Activations