© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231232
    Prev
    Next
    INDEX
    Explanations

    multi-language segments

    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_6_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
    Z
    0.92
    lar
    0.90
    N
    0.87
    ۔
    0.87
    4
    0.83
    5
    0.83
    oda
    0.82
    ulin
    0.80
    iche
    0.79
    ilik
    0.79
    POSITIVE LOGITS
     effluents
    0.97
    j
    0.88
     hypersurfaces
    0.88
    gheatmap
    0.88
    \,.
    0.87
     соответству
    0.86
     удаления
    0.85
     gleiche
    0.84
     exclu
    0.84
     fermions
    0.84
    Activations Density 0.003%

    No Known Activations