© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 197836
    Prev
    Next
    INDEX
    Explanations

    derogatory, pejorative language

    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_15_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
    קי
    0.54
    刻
    0.53
    語言
    0.51
    威
    0.51
    乗
    0.51
    μένα
    0.50
    ソース
    0.50
     negócios
    0.49
    完善
    0.48
    錬
    0.48
    POSITIVE LOGITS
    taining
    0.55
    utin
    0.52
     four
    0.50
    rating
    0.50
    ulfill
    0.49
    initely
    0.48
     parte
    0.47
    irteen
    0.47
     개의
    0.47
    pn
    0.47
    Activations Density 0.004%

    No Known Activations