© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27286
    Prev
    Next
    INDEX
    Explanations

    Brotherhood or hood

    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
    s
    1.01
     sister
    0.94
     brother
    0.91
     sisters
    0.87
     irmão
    0.86
    (
    0.84
     brothers
    0.80
     hermano
    0.79
     chị
    0.77
     hermana
    0.76
    POSITIVE LOGITS
     Será
    0.70
    ه
    0.68
    على
    0.64
    로
    0.64
    우스
    0.63
    ען
    0.58
    տ
    0.58
     ఇండి
    0.57
     permitirá
    0.57
    Jeśli
    0.57
    Activations Density 0.004%

    No Known Activations