© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205733
    Prev
    Next
    INDEX
    Explanations

    https links and markdown images

    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_20_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
    自动
    0.46
    രിച്ച
    0.45
     LOSS
    0.45
     algorithm
    0.44
    的に
    0.43
     étaient
    0.43
    }^{*}\
    0.43
    Ｑ
    0.43
    algorithm
    0.42
    чить
    0.42
    POSITIVE LOGITS
     Palladium
    0.42
     Rot
    0.42
    .{
    0.41
     oll
    0.40
     le
    0.39
     சு
    0.39
     Of
    0.39
    enance
    0.39
     Terence
    0.39
     mainstream
    0.39
    Activations Density 0.000%

    No Known Activations