© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86900
    Prev
    Next
    INDEX
    Explanations

    came down

    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_3_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
     a
    1.01
    t
    0.95
     as
    0.86
    </h2>
    0.78
    人
    0.77
    l
    0.75
    p
    0.73
     t
    0.72
     disrupt
    0.70
    ต์
    0.69
    POSITIVE LOGITS
    ación
    0.81
    increased
    0.75
    alin
    0.75
    alen
    0.74
    ances
    0.71
    ations
    0.71
     файла
    0.71
     eléctricos
    0.70
    \,\
    0.70
     மீது
    0.70
    Activations Density 0.002%

    No Known Activations