© 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. 130270
    Prev
    Next
    INDEX
    Explanations

    results

    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
    as
    1.09
    ↵
    1.01
    是
    1.00
    an
    0.98
    ่า
    0.97
    k
    0.97
    on
    0.89
    un
    0.88
    Estado
    0.86
    is
    0.84
    POSITIVE LOGITS
    ।
    1.02
     vacuoles
    0.95
    ⿶
    0.94
     aquifers
    0.92
     hoses
    0.91
     effluents
    0.91
     jugs
    0.91
     risques
    0.88
     appareils
    0.88
     argumentos
    0.88
    Activations Density 0.000%

    No Known Activations