© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3009
    Prev
    Next
    INDEX
    Explanations

    date range selection

    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_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
    ști
    0.22
    edì
    0.21
    䩕
    0.21
    ători
    0.21
    bones
    0.21
    抖
    0.20
    وين
    0.20
     uus
    0.20
    formul
    0.20
    creen
    0.20
    POSITIVE LOGITS
     செய்தது
    0.23
     Manners
    0.22
    िलास
    0.21
    娼
    0.20
    ]):
    0.20
    思議
    0.20
    }^{+}+\
    0.20
     McQu
    0.20
     sensorial
    0.20
     করিতেছে
    0.20
    Activations Density 0.001%

    No Known Activations