© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120906
    Prev
    Next
    INDEX
    Explanations

    medical contexts and lists

    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_27_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
    workspaceFolder
    0.37
    /'+
    0.31
    //
    0.30
    」
    0.30
    切り
    0.29
    poner
    0.29
    ił
    0.29
    ↵↵
    0.29
     chasing
    0.29
    window
    0.28
    POSITIVE LOGITS
    优秀的
    0.34
     различные
    0.33
    屼
    0.33
     అనేక
    0.32
    РИ
    0.32
    وتا
    0.32
    uedata
    0.32
    ΙΚ
    0.32
    郫
    0.32
    म्भ
    0.32
    Activations Density 0.003%

    No Known Activations