© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93525
    Prev
    Next
    INDEX
    Explanations

    stores and supplies

    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_11_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
     per
    0.38
     annually
    0.36
    /*
    0.35
     available
    0.35
     dahulu
    0.34
     manner
    0.34
     Per
    0.33
     в
    0.33
     mildew
    0.33
     Berry
    0.33
    POSITIVE LOGITS
    మార్
    0.47
    ലീസ്
    0.43
    ეგი
    0.43
    ГИ
    0.38
     بیشتری
    0.38
    Congress
    0.38
    Kết
    0.36
     něj
    0.36
    carbonate
    0.36
    人が
    0.35
    Activations Density 0.021%

    No Known Activations