© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 99902
    Prev
    Next
    INDEX
    Explanations

    "love you"

    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_16_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
    ७
    0.17
    镯
    0.15
     ส
    0.15
    Ớ
    0.15
    法律
    0.15
     С
    0.15
     மொழ
    0.14
     Franciscan
    0.14
    Ｃ
    0.14
     पक्ष
    0.14
    POSITIVE LOGITS
    sort
    0.17
    ကြောင့်
    0.15
    str
    0.15
     упо
    0.14
    usion
    0.14
    уга
    0.13
    upa
    0.13
    ghi
    0.13
     beforeDir
    0.13
    andu
    0.13
    Activations Density 0.008%

    No Known Activations