© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 203626
    Prev
    Next
    INDEX
    Explanations

    working together

    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
    8
    0.59
     znači
    0.59
    ស
    0.58
    та
    0.57
    스
    0.56
    ৮
    0.54
    හ
    0.54
    9
    0.53
    {
    0.53
    ز
    0.52
    POSITIVE LOGITS
    yez
    0.54
     Appodeal
    0.54
    hander
    0.50
    neapolis
    0.49
     Piala
    0.49
     uffic
    0.48
     thriller
    0.47
    incs
    0.47
    GGG
    0.47
    usal
    0.46
    Activations Density 0.003%

    No Known Activations