© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150686
    Prev
    Next
    INDEX
    Explanations

    modules

    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
     پیم
    0.38
     ['*.
    0.38
     Wim
    0.37
    ទទ
    0.37
    அல்ல
    0.37
    継
    0.37
     ialah
    0.36
    靝
    0.36
    ዮ
    0.36
     //$
    0.36
    POSITIVE LOGITS
    Module
    0.52
     Module
    0.50
     módulos
    0.49
     modules
    0.47
     module
    0.47
    Modules
    0.46
     Modules
    0.45
     modul
    0.43
    modules
    0.40
    …"
    0.40
    Activations Density 0.002%

    No Known Activations