© 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. 129203
    Prev
    Next
    INDEX
    Explanations

    which is

    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
    Not in Any Lists

    No Comments

    Negative Logits
     circunfer
    0.89
    ﺤ
    0.80
    𝒖
    0.78
     welds
    0.75
     crises
    0.74
    lays
    0.74
    まれ
    0.73
    ер
    0.71
    ει
    0.70
    عا
    0.70
    POSITIVE LOGITS
    s
    1.41
    d
    0.99
    ,
    0.99
    <0x80>
    0.98
    ב
    0.98
    '
    0.96
     in
    0.92
    ט
    0.91
    /,
    0.86
    с
    0.84
    Activations Density 0.007%

    No Known Activations