© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 5656
    Prev
    Next
    INDEX
    Explanations

    the more, the better

    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
    蜢
    0.69
    erar
    0.64
    anil
    0.63
    なりません
    0.61
    erer
    0.60
    nå
    0.59
    дання
    0.59
    arono
    0.57
    ма
    0.56
    дят
    0.56
    POSITIVE LOGITS
    fulness
    0.62
    и
    0.59
     cerca
    0.58
    গত
    0.57
    ی
    0.56
    我认为
    0.55
    hearted
    0.54
    в
    0.53
    ্ডার
    0.53
     leisure
    0.52
    Activations Density 0.014%

    No Known Activations