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. 9357
    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
    ⎪
    0.74
    נ
    0.70
    aha
    0.69
     fitted
    0.65
     ભે
    0.64
    વી
    0.63
     teknik
    0.62
     口
    0.62
     metropolis
    0.62
     advice
    0.61
    POSITIVE LOGITS
     형
    0.69
    生
    0.68
    RELATES
    0.67
    Richard
    0.65
    TeXAtom
    0.65
    ryption
    0.63
    icula
    0.63
    Pe
    0.63
     Serif
    0.63
    ForeColor
    0.63
    Activations Density 0.008%

    No Known Activations