© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 129497
    Prev
    Next
    INDEX
    Explanations

    Gaussian elimination and echelon forms

    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_25_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
     ?></
    0.44
     LOTRAchievement
    0.39
     invited
    0.39
    ኦ
    0.37
     khả
    0.37
     खैर
    0.37
     auxquels
    0.37
     pondered
    0.37
     setContentView
    0.36
     ispir
    0.36
    POSITIVE LOGITS
    TextInput
    0.40
    লার
    0.38
    扞
    0.38
    SQLite
    0.37
     nặng
    0.37
     hydrophobic
    0.36
     hydrol
    0.36
    Firing
    0.36
    ͌
    0.35
    Dias
    0.35
    Activations Density 0.001%

    No Known Activations