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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 9388
    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_31_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
    렇
    0.64
    وَ
    0.64
     পাঠকের
    0.61
    ictwo
    0.60
    ρε
    0.59
     åter
    0.59
    icularis
    0.59
    ouk
    0.58
     пле
    0.57
     Toggle
    0.57
    POSITIVE LOGITS
    ASA
    0.71
     hipster
    0.70
     huis
    0.68
    家
    0.68
    cot
    0.68
    जिटिव
    0.67
     CoA
    0.67
    屏幕
    0.66
     house
    0.66
     casa
    0.66
    Activations Density 0.227%

    No Known Activations