© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204648
    Prev
    Next
    INDEX
    Explanations

    naming conventions

    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
    b
    1.12
    at
    1.04
    in
    0.92
    J
    0.92
    ver
    0.92
    W
    0.91
    N
    0.90
    Ul
    0.89
    ank
    0.87
    Z
    0.87
    POSITIVE LOGITS
     propylene
    0.86
    .
    0.84
     моря
    0.82
     модуля
    0.82
     thuốc
    0.81
    ५
    0.79
     структуры
    0.77
     размеров
    0.76
    ますが
    0.75
     retriever
    0.75
    Activations Density 0.000%

    No Known Activations