© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24917
    Prev
    Next
    INDEX
    Explanations

    initialisms followed by explanations

    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
    ن
    0.88
    0
    0.84
    할
    0.79
    čku
    0.78
    ग
    0.75
    ت
    0.71
    ام
    0.70
    두
    0.70
    𝕝
    0.70
    बाह
    0.69
    POSITIVE LOGITS
     can
    0.85
    toare
    0.80
    s
    0.78
     are
    0.76
    town
    0.74
     chairman
    0.73
     consulting
    0.73
    י
    0.73
    k
    0.71
     complaint
    0.71
    Activations Density 0.002%

    No Known Activations