© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27759
    Prev
    Next
    INDEX
    Explanations

    SQL injection detection

    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
    ある
    0.95
    اوی
    0.93
    고
    0.89
    ری
    0.89
    い
    0.88
    ע
    0.88
    ای
    0.88
    ა
    0.88
    物の
    0.86
     razy
    0.82
    POSITIVE LOGITS
     \
    0.95
    in
    0.86
    ning
    0.82
    ch
    0.80
    ner
    0.77
    }
    0.77
    ction
    0.72
    ley
    0.71
    ”
    0.69
    }...
    0.66
    Activations Density 0.005%

    No Known Activations