© 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. 10352
    Prev
    Next
    INDEX
    Explanations

    chronic disease cure

    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
     দেখিল
    0.51
     personenbez
    0.50
    ዬ
    0.49
    يات
    0.48
    ုပ်
    0.48
     ኢ
    0.48
     médiane
    0.46
     alkot
    0.46
    ക്കാരി
    0.46
     vigilancia
    0.46
    POSITIVE LOGITS
     enfermedades
    0.73
     заболевания
    0.71
     diseases
    0.70
    v
    0.68
     Diseases
    0.67
     penyakit
    0.67
     illnesses
    0.66
     enfermedad
    0.63
     बीमारियों
    0.61
    रोग
    0.60
    Activations Density 0.039%

    No Known Activations