© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 87494
    Prev
    Next
    INDEX
    Explanations

    mathematical continuity, smoothness, and sets

    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_23_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
    👪
    0.39
    initions
    0.39
    ძლიათ
    0.38
    吆
    0.37
     সা
    0.37
     хвата
    0.37
     Стаўкі
    0.36
    decken
    0.36
    벡
    0.36
    ᇁ
    0.36
    POSITIVE LOGITS
     istem
    0.40
    ৃদ্ধ
    0.39
     perils
    0.39
    uç
    0.39
     Button
    0.37
     Como
    0.37
     histórica
    0.37
     svoju
    0.37
     svo
    0.37
     Itu
    0.37
    Activations Density 0.001%

    No Known Activations