© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44565
    Prev
    Next
    INDEX
    Explanations

    names like "amos" and "ambo" followed by "kv", "anga"

    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_3_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
    κ
    0.89
    י
    0.86
    ς
    0.75
    ی
    0.75
    да
    0.73
    ك
    0.73
    та
    0.72
    к
    0.72
    ก
    0.72
    ים
    0.71
    POSITIVE LOGITS
    "
    0.79
     judíos
    0.69
     настоя
    0.66
    mán
    0.65
    dey
    0.65
    cnt
    0.64
    दारी
    0.64
     документа
    0.63
    Jy
    0.62
     किया
    0.62
    Activations Density 0.000%

    No Known Activations