© 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. 3042
    Prev
    Next
    INDEX
    Explanations

    SQL aggregate functions

    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
    ের
    2.06
    s
    2.01
    ات
    1.93
    ñas
    1.71
    orie
    1.70
    ies
    1.64
    "%
    1.62
    만원
    1.59
    ים
    1.58
     отказа
    1.57
    POSITIVE LOGITS
    ع
    2.17
    ق
    2.12
    स्थल
    1.99
    fledged
    1.97
    rown
    1.87
     También
    1.86
    𐰣
    1.81
    корд
    1.80
    氣
    1.75
     tractable
    1.71
    Activations Density 0.005%

    No Known Activations