© 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. 43972
    Prev
    Next
    INDEX
    Explanations

    if I were

    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
     are
    1.04
     to
    0.70
     be
    0.70
     a
    0.64
    
    0.64
     mutter
    0.63
    𝟬
    0.62
     differentiate
    0.60
    логи
    0.58
     invalidate
    0.57
    POSITIVE LOGITS
    ع
    0.80
    و
    0.79
    m
    0.69
    iv
    0.68
    ம்
    0.68
    nM
    0.68
    дна
    0.66
    u
    0.65
    다
    0.65
    ца
    0.63
    Activations Density 0.006%

    No Known Activations