© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 91732
    Prev
    Next
    INDEX
    Explanations

    adult education and baby/diaper descriptors

    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
    もら
    0.66
     쉽
    0.65
     तरह
    0.60
    ubuk
    0.60
     जहाँ
    0.58
    i
    0.57
     точка
    0.54
     لینڈ
    0.52
    Kappa
    0.52
     जहां
    0.51
    POSITIVE LOGITS
     on
    1.01
     as
    0.96
    ৮
    0.74
     or
    0.73
    দের
    0.72
    он
    0.70
    رة
    0.69
    حة
    0.67
    হ
    0.67
     behandeling
    0.67
    Activations Density 0.000%

    No Known Activations