© 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-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45600
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_10_width_262k_l0_small_affine
    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
     예측
    0.51
    rneğin
    0.46
     নিজেই
    0.46
     নিজেরাই
    0.46
     পূর্বাভাস
    0.45
    图像
    0.44
    预
    0.44
     Gründe
    0.44
     badań
    0.44
     예를
    0.43
    POSITIVE LOGITS
     lately
    0.48
     ceremony
    0.47
    Holy
    0.46
     coraz
    0.46
     hinch
    0.46
     philosophy
    0.45
     altar
    0.45
     Holy
    0.44
    ጕ
    0.44
     conseiller
    0.44
    Activations Density 0.000%

    No Known Activations