© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92044
    Prev
    Next
    INDEX
    Explanations

    despise and vulgar 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_11_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
    ри
    0.89
    йти
    0.83
    ни
    0.75
    ικ
    0.68
    ти
    0.66
    ч
    0.64
    пра
    0.64
    ות
    0.64
    кти
    0.63
    ρι
    0.63
    POSITIVE LOGITS
    a
    0.75
     religion
    0.64
    </h6>
    0.63
    2
    0.61
     a
    0.61
    0.60
     TensorFlow
    0.59
     \
    0.59
     Buddhism
    0.58
    0.58
    Activations Density 0.004%

    No Known Activations