© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245835
    Prev
    Next
    INDEX
    Explanations

    presentation context

    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_40_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
    ື
    0.43
     insertar
    0.41
    Radians
    0.39
     pelaksanaan
    0.38
     moldings
    0.38
    িকপ্ট
    0.38
    迠
    0.38
    大型
    0.38
    ibir
    0.38
     پس
    0.38
    POSITIVE LOGITS
    nell
    0.41
    Trans
    0.37
     स्वातंत्र्य
    0.36
    ตำแหน่ง
    0.34
    ADO
    0.34
    相談
    0.34
    Ther
    0.33
     அடு
    0.33
    лом
    0.33
    đa
    0.33
    Activations Density 0.002%

    No Known Activations