© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134865
    Prev
    Next
    INDEX
    Explanations

    product return and recycling

    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_37_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
    uckles
    0.44
    クラブ
    0.40
     ediciones
    0.39
    槽
    0.37
     нер
    0.37
     ناح
    0.36
     ম্যা
    0.36
    
    0.35
     converted
    0.34
     속
    0.34
    POSITIVE LOGITS
     recycling
    0.89
    recycle
    0.86
    回收
    0.82
     Recycling
    0.82
     recycle
    0.80
     Recycle
    0.79
    recycl
    0.77
     recycl
    0.71
     collecte
    0.70
     recicl
    0.68
    Activations Density 0.020%

    No Known Activations