© 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. 31261
    Prev
    Next
    INDEX
    Explanations

    risk of syndrome or bleeding

    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
     책
    0.17
     thịt
    0.17
    ິ່ງ
    0.17
     Clube
    0.17
     credential
    0.17
     presc
    0.16
     addBook
    0.16
    鱈
    0.16
    坯
    0.16
    ടുന്ന
    0.16
    POSITIVE LOGITS
     soaking
    0.19
     soak
    0.18
    がありました
    0.18
    മുണ്ട
    0.17
     fostered
    0.17
     viral
    0.17
     hào
    0.17
     barley
    0.16
    ندا
    0.16
     straws
    0.16
    Activations Density 0.005%

    No Known Activations