© 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. 24-GEMMASCOPE-2-RES-262K
    7. 11970
    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_24_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
    ل
    0.79
    e
    0.77
    pset
    0.74
    ymmet
    0.70
    🎩
    0.69
    պ
    0.68
    elect
    0.67
    et
    0.66
    ppet
    0.66
     Calculate
    0.66
    POSITIVE LOGITS
     contribu
    0.83
     seorang
    0.77
    кологи
    0.75
    ത്തിൽ
    0.74
     актриса
    0.74
    ത്തില്‍
    0.73
    将于
    0.73
     joins
    0.71
     thrives
    0.70
    䤃
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.