© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215886
    Prev
    Next
    INDEX
    Explanations

    defend/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_50_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
     freaking
    0.42
     carreg
    0.38
    ទ
    0.38
     شی
    0.37
     ching
    0.37
     shi
    0.37
    ्युअर
    0.37
     നീ
    0.36
     터
    0.36
    佺
    0.36
    POSITIVE LOGITS
     defesa
    0.73
     defend
    0.67
    defense
    0.67
     defense
    0.66
     Defender
    0.66
     defence
    0.65
     defends
    0.63
     defender
    0.63
     defenders
    0.63
     defended
    0.63
    Activations Density 0.005%

    No Known Activations