© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 10420
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    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
    ется
    2.13
    🛖
    1.98
    ۥ
    1.89
    PUR
    1.88
    ‌است
    1.88
    ية
    1.84
     eléctrico
    1.82
    š
    1.80
    ਸ
    1.78
     impuestos
    1.77
    POSITIVE LOGITS
    liche
    2.16
    ли
    2.14
    <0x80>
    1.90
    ına
    1.80
    ኋላ
    1.80
    ේෂ
    1.80
     μέσα
    1.80
    endom
    1.73
    negie
    1.71
    在于
    1.70
    Activations Density 0.004%

    No Known Activations