© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 233039
    Prev
    Next
    INDEX
    Explanations

    how easy it is to

    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_6_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
     are
    0.83
    0
    0.79
    ]，
    0.78
    ERRY
    0.76
    <0x0D>
    0.72
    ]^
    0.70
     खेतों
    0.70
     เมตร
    0.70
    $
    0.70
    are
    0.69
    POSITIVE LOGITS
    c
    1.51
    h
    1.16
    p
    1.16
    ח
    1.16
    ться
    1.05
    ри
    1.03
    ৫
    1.02
    ק
    1.02
    ку
    1.01
    ز
    0.97
    Activations Density 0.003%

    No Known Activations