© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212001
    Prev
    Next
    INDEX
    Explanations

    last names or parts of names

    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_5_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
    kenalkan
    0.72
    dehyde
    0.70
    ?}",
    0.64
    ကြောင့်
    0.63
    sheet
    0.63
    ized
    0.62
     режиме
    0.62
     взя
    0.61
    ிருக்கும்
    0.61
    ية
    0.60
    POSITIVE LOGITS
    ों
    0.86
    s
    0.86
    ę
    0.77
     that
    0.74
    지
    0.74
    드
    0.74
    ă
    0.70
    ม
    0.70
    ς
    0.70
    <0x0D>
    0.69
    Activations Density 0.031%

    No Known Activations