© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1644
    Prev
    Next
    INDEX
    Explanations

    odd numbers

    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_40_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
     odd
    2.61
    Odd
    2.41
     Odd
    2.34
    odd
    2.30
    奇
    1.98
    偶
    1.82
     इवन
    1.36
     विषम
    1.20
    Even
    1.20
    EVEN
    1.17
    POSITIVE LOGITS
     ढा
    0.38
    asiswa
    0.35
     मेहन
    0.34
     काग
    0.34
     চোপ
    0.34
     rapat
    0.34
    מיני
    0.34
    専
    0.34
    نان
    0.33
     gegangen
    0.33
    Activations Density 0.046%

    No Known Activations