© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168176
    Prev
    Next
    INDEX
    Explanations

    foreseen, planned, or scheduled

    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_34_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
     deadly
    0.39
     veces
    0.38
     decid
    0.38
     pozi
    0.37
     isp
    0.37
    ␮
    0.36
     ayı
    0.36
    ὗ
    0.36
    
    0.36
    addie
    0.36
    POSITIVE LOGITS
     предусмотре
    0.74
     vorgesehen
    0.69
     предусматри
    0.59
     scheduled
    0.57
     prevista
    0.57
     prevede
    0.55
     prévu
    0.54
     included
    0.54
     передба
    0.54
     previstas
    0.54
    Activations Density 0.042%

    No Known Activations