© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178095
    Prev
    Next
    INDEX
    Explanations

    always something else exists

    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_29_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
    ùa
    0.39
     spelled
    0.38
     veut
    0.37
    aison
    0.37
    婹
    0.35
    முடைய
    0.35
    にとっては
    0.35
     presentada
    0.35
    㚐
    0.34
     veulent
    0.33
    POSITIVE LOGITS
     baguette
    0.37
    早
    0.37
    ంగ్‌
    0.37
     наблюдения
    0.37
     مخصوص
    0.37
    철
    0.37
    까지
    0.37
     மட்டும்
    0.37
    细
    0.37
     kart
    0.36
    Activations Density 0.002%

    No Known Activations