© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44194
    Prev
    Next
    INDEX
    Explanations

    symbols and code usage

    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_3_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
    a
    0.82
    ه
    0.79
    ların
    0.71
    Α
    0.71
    lished
    0.67
    lim
    0.67
    delen
    0.65
    m
    0.64
    lands
    0.61
    n
    0.61
    POSITIVE LOGITS
    да
    0.85
    ada
    0.71
    ות
    0.70
     staunch
    0.70
    দের
    0.69
     drawRight
    0.68
     eventi
    0.65
    ,
    0.64
     οποίο
    0.64
    джи
    0.63
    Activations Density 0.000%

    No Known Activations