© 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. 121651
    Prev
    Next
    INDEX
    Explanations

    ask/receive/renew

    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
    고
    0.86
    الك
    0.84
    る
    0.84
    }}$,
    0.81
    数
    0.80
    트
    0.79
    शील
    0.78
    ط
    0.78
    ل
    0.77
    ంది
    0.77
    POSITIVE LOGITS
    be
    0.77
    am
    0.66
    can
    0.66
    ка
    0.64
     в
    0.62
    genes
    0.61
    clar
    0.60
    érence
    0.60
    €™
    0.59
    wealth
    0.59
    Activations Density 0.000%

    No Known Activations