© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167144
    Prev
    Next
    INDEX
    Explanations

    sustainability initiatives and loans

    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_31_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
    URNING
    0.43
    នៅក្នុង
    0.37
    羊
    0.37
     econômica
    0.36
    ША
    0.36
    शा
    0.36
    題目
    0.36
    selectedValue
    0.36
     ekonom
    0.35
    ={},
    0.35
    POSITIVE LOGITS
     بخير
    0.42
     Laugh
    0.41
     laugh
    0.39
    一笑
    0.39
    Laugh
    0.39
     laughter
    0.38
    ค้น
    0.37
     laughed
    0.37
     laughs
    0.37
    ◐
    0.37
    Activations Density 0.002%

    No Known Activations