© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53344
    Prev
    Next
    INDEX
    Explanations

    nobody wants or needs

    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
     perfectly
    0.42
     unavoid
    0.40
     mük
    0.38
    kom
    0.38
    iped
    0.38
    ᑲ
    0.37
    豪華
    0.36
    馬上
    0.36
     ВС
    0.36
     Perfectly
    0.36
    POSITIVE LOGITS
     siquiera
    0.42
    !\
    0.39
     Daphne
    0.38
     एक्चुअली
    0.35
    ！？
    0.35
    ？？
    0.35
     mặc
    0.34
     (!
    0.34
     ಮೇ
    0.34
     Chứng
    0.34
    Activations Density 0.090%

    No Known Activations