© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14800
    Prev
    Next
    INDEX
    Explanations

    downshiftology

    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_15_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
    ,”
    0.53
     както
    0.47
     nếu
    0.46
    ”;
    0.45
    ”,
    0.45
     அனைத்தும்
    0.45
     ambiance
    0.44
    ̀ng
    0.44
     kinh
    0.43
     partea
    0.43
    POSITIVE LOGITS
    告诉我
    0.53
    േണ്ട
    0.51
    telling
    0.50
    čila
    0.47
    |$.
    0.47
    邪
    0.47
    mailbox
    0.46
    𝚖
    0.46
    想起
    0.46
    lblName
    0.46
    Activations Density 0.000%

    No Known Activations