© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37361
    Prev
    Next
    INDEX
    Explanations

    resembles a

    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_11_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
     সম্পাদিত
    0.62
     פע
    0.60
     kerana
    0.59
     herbivores
    0.59
     сфор
    0.59
     שלו
    0.58
     masukkan
    0.57
     ר
    0.57
     separados
    0.57
     사용
    0.56
    POSITIVE LOGITS
    motion
    0.65
    ك
    0.65
    junction
    0.64
    il
    0.63
    のは
    0.63
    er
    0.63
    concept
    0.63
    ح
    0.62
    truck
    0.62
    tuning
    0.61
    Activations Density 0.001%

    No Known Activations