© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3034
    Prev
    Next
    INDEX
    Explanations

    police actions and consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     самим
    0.85
    ел
    0.80
    兘
    0.79
    ست
    0.78
    ্ডার
    0.77
     successive
    0.77
    вид
    0.77
    ctors
    0.77
    ニング
    0.77
    ンダ
    0.77
    POSITIVE LOGITS
    /*
    0.71
     محصول
    0.71
    /**
    0.71
     Handlung
    0.71
    he
    0.70
    ह
    0.69
     маши
    0.69
    Rise
    0.68
     Sơn
    0.68
     nails
    0.68
    Activations Density 0.005%

    No Known Activations