© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53500
    Prev
    Next
    INDEX
    Explanations

    static

    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_55_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
    =$(
    0.37
    Grun
    0.37
     اكو
    0.37
     sánh
    0.37
    čo
    0.36
     eigenvalues
    0.35
    ^(
    0.35
     itd
    0.35
    তই
    0.34
    稟
    0.34
    POSITIVE LOGITS
     final
    1.14
     अंतिम
    1.08
    final
    0.96
     இறுதி
    0.93
    最終
    0.92
    Final
    0.91
    最后的
    0.91
     Final
    0.91
     FINAL
    0.88
     അവസാന
    0.86
    Activations Density 0.001%

    No Known Activations