© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138055
    Prev
    Next
    INDEX
    Explanations

    non-inflationary or age-related contexts

    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_12_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
    r
    0.64
    would
    0.62
    ಗೊಂಡ
    0.61
    र
    0.60
    क
    0.56
    "
    0.55
    ވާ
    0.54
    wij
    0.53
    "!
    0.53
    u
    0.53
    POSITIVE LOGITS
    Sistema
    0.58
     dostępne
    0.58
     Análisis
    0.57
     العمر
    0.57
    فير
    0.56
     Productos
    0.55
     laquelle
    0.54
     nommé
    0.54
     която
    0.53
     निभाया
    0.53
    Activations Density 0.002%

    No Known Activations