© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 44005
    Prev
    Next
    INDEX
    Explanations

    creating file system object

    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_3_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
    <0xA4>
    0.69
    Ⲁ
    0.63
    <0x96>
    0.63
    ва
    0.59
    <0x9C>
    0.56
     Rubens
    0.55
    犟
    0.55
    a
    0.55
    <0x87>
    0.53
    <0x9F>
    0.53
    POSITIVE LOGITS
    .
    0.87
    of
    0.68
     children
    0.64
    یت
    0.64
    。.
    0.64
    。"
    0.63
    లు
    0.60
     краё
    0.60
    IAN
    0.59
     national
    0.57
    Activations Density 0.001%

    No Known Activations