© 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. 40755
    Prev
    Next
    INDEX
    Explanations

    hyperloop, hyperactivity, disorder

    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
    et
    1.05
    on
    0.93
    ne
    0.91
    g
    0.86
    ли
    0.81
     on
    0.77
    ्य
    0.77
    f
    0.75
    n
    0.75
    w
    0.75
    POSITIVE LOGITS
    жда
    0.73
    是
    0.67
    ע
    0.66
    는
    0.64
    ﺃ
    0.60
     Первый
    0.59
     وهذه
    0.59
    ]]);
    0.59
    adeira
    0.58
    은
    0.58
    Activations Density 0.002%

    No Known Activations