© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206409
    Prev
    Next
    INDEX
    Explanations

    AMS airport, region, system, sickness

    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_6_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
    มัน
    0.98
    ون
    0.92
     as
    0.88
     impresa
    0.85
     angina
    0.82
     arrêt
    0.81
    น
    0.80
    什么
    0.79
     annihilation
    0.76
     ancienne
    0.75
    POSITIVE LOGITS
    L
    0.80
    5
    0.80
    };
    0.77
    c
    0.77
    S
    0.77
    N
    0.77
    4
    0.76
    ó
    0.75
    SA
    0.74
    B
    0.74
    Activations Density 0.000%

    No Known Activations