© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9102
    Prev
    Next
    INDEX
    Explanations

    Rise of [noun]

    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_13_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
     prestazioni
    0.54
    决
    0.54
     الرياضيات
    0.52
    袒
    0.52
    柣
    0.52
    <unused47>
    0.51
    <unused79>
    0.51
    واب
    0.51
    зации
    0.50
     రూ
    0.50
    POSITIVE LOGITS
     Mark
    0.55
    ит
    0.55
     mondo
    0.54
     large
    0.53
     istor
    0.53
    o
    0.53
    in
    0.52
    ido
    0.51
     Niall
    0.51
     Jenny
    0.50
    Activations Density 0.009%

    No Known Activations