© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133019
    Prev
    Next
    INDEX
    Explanations

    look no further than

    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
    dır
    0.99
    ću
    0.99
    ა
    0.99
    ți
    0.96
    ü
    0.96
    ación
    0.94
    kých
    0.94
     confining
    0.93
    ações
    0.92
    ulièrement
    0.92
    POSITIVE LOGITS
     be
    1.09
    ف
    0.95
     a
    0.93
     was
    0.91
    ้
    0.90
     all
    0.89
    </h2>
    0.89
    ர
    0.88
    لق
    0.87
    de
    0.84
    Activations Density 0.000%

    No Known Activations