© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28026
    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_40_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
     heavy
    0.46
    重
    0.46
     тяже
    0.45
     Module
    0.43
    轻
    0.42
     Мо
    0.40
     Merkez
    0.40
    輕
    0.39
    白
    0.38
    重的
    0.38
    POSITIVE LOGITS
    browserAction
    0.41
     listens
    0.39
    Comté
    0.39
    JVM
    0.38
    ரிகிறது
    0.37
    Count
    0.37
     평균
    0.36
    वाती
    0.36
     বিশ্লে
    0.36
    市值
    0.36
    Activations Density 0.000%

    No Known Activations