© 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
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81716
    Prev
    Next
    INDEX
    Explanations

    string theory or string handling

    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_0_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
    с
    1.69
    {
    1.61
    ين
    1.55
    ية
    1.52
    人
    1.45
    ро
    1.36
     are
    1.32
    س
    1.31
     in
    1.30
    é
    1.30
    POSITIVE LOGITS
    یم
    1.34
     for
    1.32
    ま
    1.30
    ）；
    1.24
    ור
    1.21
     взя
    1.19
     instal
    1.17
    ять
    1.16
     For
    1.15
    いです
    1.12
    Activations Density 0.005%

    No Known Activations