© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39262
    Prev
    Next
    INDEX
    Explanations

    lgbtq

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    gf
    0.56
    gan
    0.52
    գ
    0.51
    ғ
    0.50
     gf
    0.50
    GU
    0.49
    gow
    0.48
    GO
    0.48
    gpu
    0.47
    ге
    0.47
    POSITIVE LOGITS
    ئو
    0.42
     উত্তেজিত
    0.40
    ስማ
    0.38
    merce
    0.37
    بت
    0.37
    zit
    0.37
     Франция
    0.36
    ˢ
    0.36
    ئت
    0.35
     BET
    0.35
    Activations Density 0.006%

    No Known Activations