© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64598
    Prev
    Next
    INDEX
    Explanations

    soil

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    溆
    0.36
    塡
    0.35
     сда
    0.34
    栅
    0.34
    ricos
    0.34
    ঠু
    0.33
    囊
    0.33
    浻
    0.33
     রাক
    0.33
    ulagway
    0.32
    POSITIVE LOGITS
     soil
    2.33
     Soil
    2.14
    soil
    2.13
    Soil
    2.11
    土壤
    1.78
     soils
    1.67
     suelo
    1.66
     Soils
    1.50
     خاک
    1.37
     suelos
    1.35
    Activations Density 0.020%

    No Known Activations