© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58150
    Prev
    Next
    INDEX
    Explanations

    SE followed by other letters or words

    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_11_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
     потер
    0.29
     activa
    0.29
     prevenção
    0.29
    ل
    0.28
     актива
    0.28
     загру
    0.26
     pérdida
    0.26
    <0x80>
    0.25
     மாநில
    0.25
    ก
    0.25
    POSITIVE LOGITS
    psi
    0.34
    SD
    0.33
     L
    0.30
    5
    0.29
    P
    0.29
    E
    0.29
    EE
    0.28
    0.28
    da
    0.28
    DI
    0.28
    Activations Density 0.006%

    No Known Activations