© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48026
    Prev
    Next
    INDEX
    Explanations

    the most obvious

    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_10_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
    apas
    0.65
    事業
    0.61
    म
    0.60
    ありません
    0.59
    ментов
    0.59
    מ
    0.57
    ਾਲ
    0.56
    ;
    0.56
     is
    0.55
    मय
    0.55
    POSITIVE LOGITS
    at
    0.94
     correcta
    0.75
     P
    0.74
     Brownian
    0.71
     Probab
    0.71
    section
    0.70
     Oceania
    0.69
    }",
    0.68
     weil
    0.68
    et
    0.67
    Activations Density 0.003%

    No Known Activations