© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74797
    Prev
    Next
    INDEX
    Explanations

    and

    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_31_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
    Xaml
    0.47
    ूँ
    0.42
    webpack
    0.40
    iint
    0.39
     bele
    0.38
     dividir
    0.38
     respet
    0.37
    \|\
    0.36
    |\
    0.36
    QPushButton
    0.36
    POSITIVE LOGITS
     Along
    0.43
     LENGTH
    0.40
     length
    0.40
     আরম্ভ
    0.39
     길이가
    0.39
     vozila
    0.39
     길이
    0.39
    截
    0.38
    length
    0.37
     đoạn
    0.37
    Activations Density 0.017%

    No Known Activations