© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 43972
    Prev
    Next
    INDEX
    Explanations

    ineffable

    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_13_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
    mentation
    0.57
    تا
    0.48
     ta
    0.46
     pokazuje
    0.44
     ආ
    0.43
     cik
    0.42
    thin
    0.42
    érêt
    0.42
     latter
    0.41
     مت
    0.41
    POSITIVE LOGITS
     ISBN
    0.61
     Según
    0.57
     Paul
    0.53
     WLAN
    0.53
    Wireless
    0.53
    e
    0.53
     Notable
    0.51
     Inggris
    0.51
     BST
    0.50
     Велико
    0.50
    Activations Density 0.000%

    No Known Activations