© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204134
    Prev
    Next
    INDEX
    Explanations

    nuts, seeds, or berries

    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
     leaflets
    0.42
     каль
    0.39
     calc
    0.38
    钙
    0.38
     Calc
    0.37
    ẩm
    0.37
     leaflet
    0.37
    brero
    0.36
    iched
    0.35
     lifestyle
    0.35
    POSITIVE LOGITS
    ผ่าน
    0.38
     Darren
    0.38
    الحكم
    0.37
    DAR
    0.36
    㯎
    0.36
    },{
    0.36
     incentivize
    0.36
     казах
    0.36
    ダーク
    0.36
     Татар
    0.34
    Activations Density 0.003%

    No Known Activations