© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56991
    Prev
    Next
    INDEX
    Explanations

    underserved communities and market

    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_11_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
     surgeon
    0.61
     cardiop
    0.59
    ↵
    0.55
     तथ्यों
    0.55
     सर्जरी
    0.54
    髖
    0.54
     surgeons
    0.53
    Snippet
    0.52
     genetics
    0.51
    审批
    0.51
    POSITIVE LOGITS
    м
    0.57
    em
    0.57
     madrugada
    0.57
    on
    0.52
    uz
    0.51
    ac
    0.50
     Mazda
    0.50
    instead
    0.50
    LookAndFeel
    0.50
    ax
    0.49
    Activations Density 0.006%

    No Known Activations