© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209817
    Prev
    Next
    INDEX
    Explanations

    scientific consensus and principles

    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_20_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
    ITO
    0.46
     boja
    0.40
    ito
    0.39
    րա
    0.38
     among
    0.38
     họp
    0.38
    心
    0.37
    ダル
    0.37
     فضای
    0.37
    among
    0.36
    POSITIVE LOGITS
    rüstung
    0.47
    )<\
    0.45
     verfü
    0.45
     Ranger
    0.44
     beschik
    0.43
    RANGER
    0.43
     রাত্রি
    0.43
     Hö
    0.42
     ලබා
    0.41
     ස්ථා
    0.40
    Activations Density 0.002%

    No Known Activations