© 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-16K
    7. 4536
    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_16k_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
    Хо
    0.64
    Pren
    0.64
    ف
    0.64
     ക്
    0.64
    ostiene
    0.64
    پ
    0.62
    
    0.62
    iboard
    0.62
    akana
    0.62
    ocaust
    0.61
    POSITIVE LOGITS
     aforementioned
    0.66
     use
    0.65
     andre
    0.63
     the
    0.62
     der
    0.62
     dùng
    0.62
     👉
    0.61
     como
    0.59
     various
    0.59
     calling
    0.59
    Activations Density 0.994%

    No Known Activations