© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215288
    Prev
    Next
    INDEX
    Explanations

    Nagios Core XI

    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_5_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
     hypersurfaces
    1.08
    ut
    1.01
    发
    1.00
    할
    1.00
    ور
    0.99
    ئن
    0.98
    中
    0.98
    وس
    0.97
     चिकित्सक
    0.96
    م
    0.96
    POSITIVE LOGITS
     an
    1.15
     don
    1.13
     není
    1.05
    STER
    1.03
     a
    1.02
     dupa
    1.00
     you
    0.98
     što
    0.97
     have
    0.95
    לי
    0.93
    Activations Density 0.000%

    No Known Activations