© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43041
    Prev
    Next
    INDEX
    Explanations

    titanium alloys

    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_13_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
    right
    0.29
    </h3>
    0.29
    return
    0.29
     Dei
    0.28
    who
    0.28
    wal
    0.28
    </h1>
    0.27
     who
    0.27
    tau
    0.27
    ów
    0.27
    POSITIVE LOGITS
     Efforts
    0.29
    ዎችን
    0.27
     използва
    0.27
    >\<^
    0.27
     Assistance
    0.26
     commonplace
    0.26
     cửa
    0.25
     Visits
    0.25
    พวก
    0.25
     nổi
    0.25
    Activations Density 0.002%

    No Known Activations