© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61553
    Prev
    Next
    INDEX
    Explanations

    data, standards, literature, and recommendations

    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_11_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
    零部件
    0.34
     мо
    0.33
    й
    0.32
     loops
    0.31
    ートル
    0.31
     Outputs
    0.31
     undirected
    0.31
    ン
    0.31
    ર
    0.31
     ПО
    0.31
    POSITIVE LOGITS
    able
    0.37
    accep
    0.35
     će
    0.32
    ampak
    0.31
    ere
    0.31
    June
    0.31
    '
    0.30
    prise
    0.30
    ited
    0.30
     näher
    0.30
    Activations Density 0.034%

    No Known Activations