© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201930
    Prev
    Next
    INDEX
    Explanations

    federated learning clients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    ผลิต
    0.42
     вироб
    0.41
     ОК
    0.40
     tumble
    0.40
     производстве
    0.40
    ент
    0.40
    賣
    0.39
     produite
    0.39
     mumkin
    0.39
    ippi
    0.38
    POSITIVE LOGITS
     Strong
    0.40
    袅
    0.36
     kon
    0.36
     conviction
    0.36
    Strong
    0.36
     beats
    0.35
     keuangan
    0.35
     Demon
    0.34
     kiến
    0.34
     kehidupan
    0.34
    Activations Density 0.001%

    No Known Activations