© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 65611
    Prev
    Next
    INDEX
    Explanations

    build commands

    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_51_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
    ল্যান্ড
    0.44
    abad
    0.39
    oder
    0.38
    ologue
    0.38
     land
    0.37
    ovost
    0.37
     trag
    0.37
     요
    0.37
     pad
    0.37
    ucket
    0.37
    POSITIVE LOGITS
    ﺳ
    0.47
    ўнай
    0.43
    =\"
    0.42
    Gateway
    0.39
    Jac
    0.38
    haften
    0.38
    స్ట్
    0.37
    <unused624>
    0.37
    intre
    0.37
     ја
    0.37
    Activations Density 0.001%

    No Known Activations