© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37075
    Prev
    Next
    INDEX
    Explanations

    names of famous people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    SEM
    0.62
    ской
    0.58
     I
    0.56
     YOU
    0.56
    rule
    0.55
     ."
    0.55
    는
    0.55
    не
    0.55
     În
    0.55
     Seç
    0.55
    POSITIVE LOGITS
    kiej
    0.61
     bruta
    0.61
    al
    0.59
     strips
    0.58
     acides
    0.56
    ဝ
    0.56
    ataan
    0.55
     comple
    0.54
    kiego
    0.54
     partiellement
    0.54
    Activations Density 0.001%

    No Known Activations