© 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. 41954
    Prev
    Next
    INDEX
    Explanations

    real power, electric charges

    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
    ра
    0.94
    де
    0.82
    e
    0.81
    vény
    0.75
    a
    0.74
    f
    0.72
    し
    0.71
    ſe
    0.66
    ా
    0.65
    on
    0.65
    POSITIVE LOGITS
     групи
    0.61
     attribut
    0.57
    nem
    0.57
     relais
    0.55
     predominate
    0.55
     détermine
    0.54
     informasi
    0.54
    nama
    0.54
     conver
    0.52
     dominate
    0.52
    Activations Density 0.008%

    No Known Activations