© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130785
    Prev
    Next
    INDEX
    Explanations

    foreign language terms definitions

    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_6_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
     که
    0.81
    _
    0.78
     što
    0.77
    (),
    0.76
     ৃ
    0.76
     OF
    0.74
    zieć
    0.71
     کہ
    0.71
    ۰
    0.71
     you
    0.70
    POSITIVE LOGITS
    高手
    0.70
    少量
    0.68
    することは
    0.67
    k
    0.67
    事
    0.66
    影响
    0.64
     tonnage
    0.64
    ड
    0.64
    م
    0.64
    ことも
    0.63
    Activations Density 0.000%

    No Known Activations