© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 213873
    Prev
    Next
    INDEX
    Explanations

    Jo Jo

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Anne
    0.48
    <0x8E>
    0.44
    bib
    0.43
    Anno
    0.42
    랍
    0.42
    विश्
    0.42
    nea
    0.41
    षिक
    0.41
    히
    0.41
    iglio
    0.41
    POSITIVE LOGITS
    ุ่ม
    0.42
    verticalLayout
    0.39
     Brooklyn
    0.38
     politician
    0.38
     రాజకీయ
    0.38
     politics
    0.38
     Buffered
    0.38
     grac
    0.38
     মুজিবুর
    0.37
     Politics
    0.37
    Activations Density 0.000%

    No Known Activations