© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18006
    Prev
    Next
    INDEX
    Explanations

    data structures, class definitions

    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_15_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
    ulfillment
    0.33
    havior
    0.31
    টিশ
    0.29
    several
    0.29
     بابەت
    0.29
    facilit
    0.29
    ]
    0.29
     مسئله
    0.28
    ting
    0.28
    ปัญหา
    0.28
    POSITIVE LOGITS
     senza
    0.30
     తమి
    0.30
     chimneys
    0.30
     mortgages
    0.30
     WANT
    0.30
     viscose
    0.30
    迄
    0.30
     comedians
    0.30
     করেনি
    0.29
     Berkeley
    0.29
    Activations Density 0.034%

    No Known Activations