© 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. 162762
    Prev
    Next
    INDEX
    Explanations

    boundaries or domestic relationships

    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
     pregnant
    0.95
     pregnancy
    0.91
     Pregnancy
    0.90
     Pregnant
    0.88
     maternity
    0.83
     pregnancies
    0.82
    pregnant
    0.79
    🤰
    0.79
    Pregnant
    0.79
    妊
    0.78
    POSITIVE LOGITS
    boundaries
    0.44
     doma
    0.41
    Boundary
    0.40
     Boundaries
    0.40
     ভাগের
    0.38
     Boundary
    0.37
     classpath
    0.37
    ﹍
    0.36
     بھائی
    0.36
    BOUNDARY
    0.35
    Activations Density 0.028%

    No Known Activations