© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141422
    Prev
    Next
    INDEX
    Explanations

    составить, составлять, compose, compiled

    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_12_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
    “
    0.57
    f
    0.56
     със
    0.54
     massima
    0.54
    .
    0.53
    ，“
    0.53
    tut
    0.53
    an
    0.52
    .“
    0.52
     πως
    0.52
    POSITIVE LOGITS
    ா
    0.65
    ontrol
    0.59
    ద
    0.57
     Launches
    0.54
    ка
    0.53
    ви
    0.52
    ち
    0.50
    сле
    0.50
    ки
    0.49
    ர்
    0.49
    Activations Density 0.001%

    No Known Activations