© 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. 134680
    Prev
    Next
    INDEX
    Explanations

    explosive power

    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
    ਰ
    0.96
    ियों
    0.89
    ных
    0.82
     Еще
    0.79
     Рас
    0.77
    ные
    0.76
    ých
    0.75
    ných
    0.74
    LatLng
    0.71
    메이션
    0.71
    POSITIVE LOGITS
    s
    1.20
    ing
    1.05
            
    0.87
    7
    0.87
    8
    0.86
    ्स
    0.85
    e
    0.82
    4
    0.81
    er
    0.80
    k
    0.80
    Activations Density 0.001%

    No Known Activations