© 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. 33459
    Prev
    Next
    INDEX
    Explanations

    nbtstat, ndt, nvt, npa, nrf

    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
    freq
    0.67
     ہوگا۔
    0.66
    s
    0.64
    CANCEL
    0.64
    ту
    0.63
    centre
    0.63
    ATIONAL
    0.63
    copper
    0.63
    обще
    0.62
    TEMP
    0.62
    POSITIVE LOGITS
    '
    1.01
    ৯
    0.82
    ,
    0.77
    ’
    0.73
    -
    0.71
     จ
    0.66
    ות
    0.62
     Stat
    0.59
    ول
    0.59
    \
    0.58
    Activations Density 0.001%

    No Known Activations