© 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. 128059
    Prev
    Next
    INDEX
    Explanations

    without ever

    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
    Negative Logits
    n
    0.79
    á
    0.78
    ä
    0.76
    í
    0.75
    j
    0.73
     L
    0.71
     l
    0.71
     been
    0.71
    ě
    0.71
    ري
    0.70
    POSITIVE LOGITS
    ма
    0.80
    کنندگان
    0.70
    حظ
    0.64
    quakes
    0.62
    یسی
    0.61
    дации
    0.61
    acariy
    0.59
    کرات
    0.59
    不由
    0.57
    ξεις
    0.57
    Activations Density 0.002%

    No Known Activations