© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 107626
    Prev
    Next
    INDEX
    Explanations

    LGBTQ+ community and representation

    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_1_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
    t
    1.56
    ش
    1.53
    la
    1.12
    ש
    1.09
    j
    1.09
     The
    1.07
    ع
    1.03
    в
    0.98
    n
    0.97
    }
    0.97
    POSITIVE LOGITS
    ۹
    1.05
    ጕ
    0.98
    ቒ
    0.95
    ۳
    0.86
    ца
    0.83
    ್ಧ
    0.83
    ाग्राम
    0.82
    ርዓ
    0.82
    -\
    0.81
    ados
    0.81
    Activations Density 0.003%

    No Known Activations