© 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. 17945
    Prev
    Next
    INDEX
    Explanations

    lone pair on nitrogen

    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
     soap
    0.73
    洗
    0.68
    Soap
    0.64
     洗
    0.62
     soaps
    0.62
     washing
    0.60
     Soap
    0.59
    🧼
    0.59
     wash
    0.59
    soap
    0.57
    POSITIVE LOGITS
    <unused2111>
    0.41
     wardrobes
    0.40
    燒
    0.39
    古墳
    0.38
     Habits
    0.38
     เกม
    0.38
     NÃO
    0.38
     wardrobe
    0.37
    seud
    0.37
     स्टूडियो
    0.37
    Activations Density 0.008%

    No Known Activations