© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24316
    Prev
    Next
    INDEX
    Explanations

    sister

    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_10_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
     (
    0.86
     brother
    0.77
     sister
    0.64
     stepfather
    0.64
    brother
    0.63
     twin
    0.63
     brothers
    0.61
     cousin
    0.61
     C
    0.60
     duvet
    0.60
    POSITIVE LOGITS
    л
    0.80
    it
    0.78
    ע
    0.78
    0
    0.77
    ０
    0.75
    ع
    0.73
    at
    0.72
    器
    0.72
    ל
    0.69
    ن
    0.68
    Activations Density 0.004%

    No Known Activations