© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146169
    Prev
    Next
    INDEX
    Explanations

    cross-site scripting

    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_0_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
    s
    2.66
    am
    1.68
    en
    1.64
    ak
    1.60
    um
    1.49
    1
    1.48
    have
    1.47
    on
    1.44
    as
    1.41
     have
    1.40
    POSITIVE LOGITS
    ج
    1.99
    리
    1.57
    ע
    1.26
    ם
    1.22
    ון
    1.20
    ين
    1.20
    י
    1.17
    ص
    1.16
    ิ
    1.16
    .
    1.16
    Activations Density 0.000%

    No Known Activations