© 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. 3138
    Prev
    Next
    INDEX
    Explanations

    tsundere comics

    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
     haloes
    0.68
    有多少
    0.62
    ে
    0.62
    ến
    0.62
    omerang
    0.61
     vực
    0.61
    拍摄
    0.57
    ುವ
    0.57
     terminó
    0.57
     基于
    0.57
    POSITIVE LOGITS
    𝚎
    0.68
    ////////////
    0.66
    ка
    0.66
    р
    0.64
     וכ
    0.60
    ृ
    0.60
    τερ
    0.59
    ра
    0.56
    cun
    0.56
     jPanel
    0.54
    Activations Density 0.004%

    No Known Activations