© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7738
    Prev
    Next
    INDEX
    Explanations

    change or shift

    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_3_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
    ق
    0.89
    ли
    0.88
    ored
    0.82
    ك
    0.80
     attentive
    0.79
    да
    0.78
     curcumin
    0.77
    kz
    0.77
     ankle
    0.77
     translateY
    0.75
    POSITIVE LOGITS
    ことです
    0.90
     причем
    0.90
    ことになる
    0.80
    こと
    0.79
     যাইহোক
    0.75
    ここ
    0.75
    ו
    0.74
    يد
    0.72
    种
    0.70
     অন্যদিকে
    0.69
    Activations Density 0.043%

    No Known Activations