© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196599
    Prev
    Next
    INDEX
    Explanations

    Soviet resistance exploited operations

    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_15_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
    ł
    0.17
    ki
    0.17
    bor
    0.17
    kol
    0.17
    be
    0.17
    ard
    0.17
    ole
    0.16
    .<
    0.16
    á
    0.16
    ī
    0.16
    POSITIVE LOGITS
     databases
    0.17
     softwares
    0.17
     operas
    0.15
     burials
    0.15
     romances
    0.15
    ীতে
    0.15
     amas
    0.15
     मचा
    0.15
     encrypt
    0.15
     étrang
    0.14
    Activations Density 0.001%

    No Known Activations