© 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. 206117
    Prev
    Next
    INDEX
    Explanations

    waste to landfill

    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
    分离
    0.45
     Separation
    0.41
     separa
    0.41
    hw
    0.40
    مون
    0.39
    コマ
    0.39
     sépar
    0.38
    赊
    0.38
    빽
    0.38
     Mammoth
    0.38
    POSITIVE LOGITS
     landfill
    0.83
     landfills
    0.71
    Trash
    0.55
     Trash
    0.52
     disposal
    0.52
    垃圾
    0.51
     trash
    0.50
     Disposal
    0.49
     inc
    0.46
     basura
    0.45
    Activations Density 0.001%

    No Known Activations