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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3523
    Prev
    Next
    INDEX
    Explanations

    antd and Design

    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
    en
    0.68
    afstand
    0.68
    лика
    0.66
    াজার
    0.65
    duit
    0.64
    𝒅
    0.63
     aro
    0.62
     pliers
    0.61
    ника
    0.61
    лению
    0.60
    POSITIVE LOGITS
    帜
    0.69
    קים
    0.62
    ബരിമല
    0.62
     असल्याने
    0.58
     Niño
    0.58
    ということは
    0.58
     memperhatikan
    0.58
     всего
    0.57
     博文
    0.56
    و
    0.56
    Activations Density 0.002%

    No Known Activations