© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88635
    Prev
    Next
    INDEX
    Explanations

    commands to start actions

    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_23_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
     []);
    0.37
    בי
    0.37
     শিরোনাম
    0.35
     sebelumnya
    0.34
    不需要
    0.34
     it
    0.34
     a
    0.33
     유사
    0.33
    যেন
    0.33
    дной
    0.33
    POSITIVE LOGITS
    ങ്ങ്
    0.43
     tighten
    0.40
     organize
    0.39
     utilisez
    0.39
     make
    0.38
     mettere
    0.38
    Make
    0.37
     اكتب
    0.37
     استخدم
    0.37
    жмите
    0.37
    Activations Density 0.138%

    No Known Activations