© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 251537
    Prev
    Next
    INDEX
    Explanations

    guard

    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_56_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
    Gu
    2.83
     gu
    2.80
    gu
    2.67
     Gu
    2.63
    GU
    2.09
     GU
    2.08
     гу
    1.79
    顾
    1.72
     guava
    1.67
     गु
    1.65
    POSITIVE LOGITS
     guarded
    0.84
     gard
    0.80
     Gard
    0.80
    警
    0.80
     guarding
    0.78
     garde
    0.76
     Gardener
    0.71
     garder
    0.70
     Gardner
    0.68
     guard
    0.68
    Activations Density 0.000%

    No Known Activations