© 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. 48899
    Prev
    Next
    INDEX
    Explanations

    configuration settings

    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
    తున్నారు
    0.32
    からです
    0.32
    पंजाब
    0.30
     marcador
    0.30
     सैंपल
    0.30
    ಔ
    0.30
     administrator
    0.29
     কালী
    0.29
     Schub
    0.29
     préciser
    0.29
    POSITIVE LOGITS
    ória
    0.34
     sto
    0.28
     >
    0.27
     riv
    0.27
     boto
    0.27
     بھر
    0.27
     Chamb
    0.27
    শ্ত
    0.27
    加盟
    0.27
     pořád
    0.27
    Activations Density 0.001%

    No Known Activations