© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17001
    Prev
    Next
    INDEX
    Explanations

    creens

    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
    ль
    0.59
    出
    0.54
     أس
    0.53
     再
    0.51
     എൻ
    0.51
     dà
    0.51
     المط
    0.51
    地
    0.51
     سند
    0.50
    зно
    0.50
    POSITIVE LOGITS
     Aces
    0.58
     tubes
    0.54
     Panels
    0.54
     চ
    0.53
     panels
    0.52
     методом
    0.52
     lumea
    0.51
     Scripts
    0.50
     logins
    0.50
    ત
    0.49
    Activations Density 0.019%

    No Known Activations