© 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. 46039
    Prev
    Next
    INDEX
    Explanations

    grid container color array operators

    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
     człowie
    0.70
     humanas
    0.64
     múltipl
    0.60
    东西
    0.59
     それ
    0.59
     функция
    0.59
     oznac
    0.59
     ១
    0.58
     trzech
    0.57
     мини
    0.57
    POSITIVE LOGITS
    the
    0.97
    it
    0.96
    ol
    0.87
    ot
    0.87
    ur
    0.86
    ay
    0.83
    t
    0.80
    an
    0.80
    ad
    0.77
    c
    0.76
    Activations Density 0.001%

    No Known Activations