© 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. 122354
    Prev
    Next
    INDEX
    Explanations

    C/c programming language code

    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
     second
    0.87
    τη
    0.82
     Second
    0.81
     segunda
    0.81
     vigilancia
    0.81
    りと
    0.80
     monotonous
    0.79
    б
    0.79
     segundo
    0.77
    트를
    0.77
    POSITIVE LOGITS
    ,
    0.90
    ir
    0.81
    सी
    0.78
    لی
    0.76
    ン
    0.75
    سی
    0.71
    cych
    0.71
     Każ
    0.70
    h
    0.70
    ‌ای
    0.70
    Activations Density 0.006%

    No Known Activations