© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 6747
    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
     extrapol
    0.91
    鸪
    0.90
     hyperlinks
    0.90
     macromolecules
    0.89
     slogans
    0.89
     undead
    0.89
    <unused2183>
    0.89
     grenades
    0.87
     actinides
    0.86
     dichloromethane
    0.85
    POSITIVE LOGITS
    Il
    0.73
    ip
    0.72
    I
    0.72
    inu
    0.71
    con
    0.70
    icket
    0.70
    boost
    0.68
    benefit
    0.68
    itor
    0.67
    ida
    0.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.