© 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. 41339
    Prev
    Next
    INDEX
    Explanations

    formation, formulation, formalization

    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
    ิ
    1.16
    ד
    0.92
    ע
    0.76
    ל
    0.75
    اتی
    0.73
    น
    0.68
    '
    0.67
    ص
    0.66
    ası
    0.66
    تين
    0.64
    POSITIVE LOGITS
    formul
    0.82
     fórmulas
    0.77
    o
    0.75
     formatos
    0.74
    Form
    0.73
    forming
    0.71
    formulario
    0.71
     formul
    0.70
    pping
    0.70
    Formula
    0.70
    Activations Density 0.031%

    No Known Activations