© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138245
    Prev
    Next
    INDEX
    Explanations

    defense

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Suy
    0.38
    fromCharCode
    0.36
    亅
    0.35
    籹
    0.34
    িট
    0.34
     сторону
    0.34
    蕌
    0.34
    ियोग्राफी
    0.33
    㑨
    0.33
     castor
    0.33
    POSITIVE LOGITS
     defense
    2.77
     defence
    2.63
    defense
    2.45
    Defense
    2.44
     Defense
    2.42
     Defence
    2.31
    Defence
    2.30
    defence
    2.23
     defensa
    2.14
     defesa
    2.11
    Activations Density 0.027%

    No Known Activations