© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41274
    Prev
    Next
    INDEX
    Explanations

    fire rated, away, firewhiskey, firehouse, firestopping

    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
    ;
    1.02
    ,
    0.93
    ?
    0.80
     niiden
    0.77
     roue
    0.73
     antara
    0.70
    :
    0.70
     mudar
    0.69
     déplacer
    0.69
     facture
    0.69
    POSITIVE LOGITS
    س
    0.89
    s
    0.83
    v
    0.74
     a
    0.74
    transformed
    0.73
    transform
    0.72
    ق
    0.71
    msg
    0.71
    class
    0.70
    mu
    0.70
    Activations Density 0.002%

    No Known Activations