Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15171
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_19_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
     시즌
    0.75
     supplied
    0.71
     langt
    0.69
     settimane
    0.68
     resten
    0.66
    季度
    0.66
    opropyl
    0.65
     날
    0.65
    ബ്
    0.64
     compound
    0.64
    POSITIVE LOGITS
    Burn
    0.81
    Instituto
    0.77
    INST
    0.74
     ഔ
    0.73
     его
    0.73
    Dom
    0.72
    Burning
    0.72
     людей
    0.71
    abandon
    0.70
    Inc
    0.69
    Activations Density 0.000%

    No Known Activations