© 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. 24689
    Prev
    Next
    INDEX
    Explanations

    parties involved

    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
    ם
    0.73
    мерикан
    0.68
    ри
    0.68
    ية
    0.68
    oje
    0.67
    ן
    0.65
    ní
    0.62
    Pathway
    0.61
    dür
    0.61
    TS
    0.60
    POSITIVE LOGITS
    ק
    0.70
    s
    0.68
    ی
    0.67
     parties
    0.63
     anten
    0.62
    ang
    0.59
    ات
    0.59
    ad
    0.57
     tämän
    0.57
     delici
    0.55
    Activations Density 0.014%

    No Known Activations