© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139571
    Prev
    Next
    INDEX
    Explanations

    Sure capit warz mode

    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
     Aqui
    0.50
     echoed
    0.49
     chegou
    0.48
     Ако
    0.48
     falou
    0.47
     ವೈ
    0.47
    𝚌
    0.46
     infringing
    0.46
     İş
    0.46
     ಉಪ
    0.46
    POSITIVE LOGITS
    طر
    0.49
    Smoke
    0.49
    Selector
    0.47
    Col
    0.47
    Т
    0.47
    Renderer
    0.46
    लाम
    0.46
     wilds
    0.45
     গ্রন্
    0.45
    igel
    0.44
    Activations Density 0.000%

    No Known Activations