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. 9318
    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
     अत्य
    0.66
     dangerous
    0.64
    dangerous
    0.64
     dangereux
    0.60
     էր
    0.60
    ⁧
    0.60
     বিপ্লবী
    0.58
     incroy
    0.58
     मुआवजा
    0.57
    ৳
    0.57
    POSITIVE LOGITS
     pretty
    1.71
    Pretty
    1.63
     Pretty
    1.61
    pretty
    1.49
     fun
    0.97
     Fun
    0.94
    fun
    0.94
    Fun
    0.89
     FUN
    0.86
     Proper
    0.80
    Activations Density 0.261%

    No Known Activations