© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45857
    Prev
    Next
    INDEX
    Explanations

    unwanted sexual thoughts or contact

    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
    醎
    0.63
    ವಾರು
    0.60
    apayati
    0.59
    मधील
    0.59
    দিগের
    0.58
    ASTIC
    0.58
    V
    0.58
    lari
    0.57
    കൊണ്ട്
    0.57
    ক্ষেত্র
    0.56
    POSITIVE LOGITS
    '
    0.87
     can
    0.83
     كان
    0.73
    在
    0.70
     في
    0.68
     was
    0.64
    大
    0.64
    oh
    0.62
    ५
    0.61
    ۵
    0.61
    Activations Density 0.005%

    No Known Activations