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. 9306
    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
     була
    0.70
    タブ
    0.69
     ৰ
    0.62
    杨
    0.62
     قال
    0.62
     torpedo
    0.61
    Жи
    0.61
     Ось
    0.61
     የ
    0.60
    btnLogin
    0.60
    POSITIVE LOGITS
     por
    0.94
     para
    0.84
     nos
    0.77
     como
    0.76
     contra
    0.75
     que
    0.73
     در
    0.72
     entre
    0.67
    ными
    0.63
     pores
    0.62
    Activations Density 0.077%

    No Known Activations