© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 60116
    Prev
    Next
    INDEX
    Explanations

    could

    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_59_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
     အတွ
    0.44
     writeFile
    0.40
     gazebo
    0.39
    </h3>
    0.38
     तस्वीर
    0.37
    </h4>
    0.37
    ೂರ್
    0.36
     lanzar
    0.36
    အတွက်
    0.35
     mesure
    0.35
    POSITIVE LOGITS
     *,
    0.86
     ،
    0.85
     ,
    0.82
     ，
    0.82
    $,
    0.80
     ,"
    0.74
     —,
    0.70
     ၊
    0.70
     (),
    0.69
     ”,
    0.68
    Activations Density 0.011%

    No Known Activations