© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123278
    Prev
    Next
    INDEX
    Explanations

    microgravity or microfiber cloth

    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_3_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
     любо
    0.61
     for
    0.59
    िग
    0.58
    rict
    0.57
    rific
    0.57
    յ
    0.57
    lin
    0.57
    ina
    0.56
    iv
    0.55
    oe
    0.55
    POSITIVE LOGITS
    ক
    0.79
    س
    0.78
    ق
    0.77
    Vous
    0.77
    দ
    0.74
    স
    0.71
    Д
    0.71
    Existe
    0.70
    ו
    0.70
    Sehr
    0.68
    Activations Density 0.000%

    No Known Activations