© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34303
    Prev
    Next
    INDEX
    Explanations

    promiscuous and related suffixes/forms

    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_7_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
    О
    0.95
    К
    0.84
    O
    0.82
    С
    0.80
    ب
    0.79
    Т
    0.79
    Мы
    0.76
    Пер
    0.75
    Го
    0.75
    Для
    0.75
    POSITIVE LOGITS
    0.82
    ic
    0.70
     can
    0.64
    ed
    0.64
    -
    0.61
     a
    0.58
     disparity
    0.58
     chilli
    0.58
    ad
    0.57
     conglomerate
    0.57
    Activations Density 0.003%

    No Known Activations