© 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. 12178
    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
    一种
    0.80
    其他
    0.74
     more
    0.66
    一種
    0.66
    らの
    0.66
    Anyone
    0.65
    或
    0.65
    这种
    0.64
     Figure
    0.64
    黏
    0.64
    POSITIVE LOGITS
    idah
    0.79
    asih
    0.75
    ୍
    0.72
     micró
    0.71
    gram
    0.71
    sockets
    0.71
    লীগের
    0.70
     jungles
    0.70
     gingen
    0.70
     byteArray
    0.70
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.