© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 198871
    Prev
    Next
    INDEX
    Explanations

    description of phrase

    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
    ieved
    0.61
     Gosudarstvennyj
    0.54
    ర్‌లో
    0.44
    ненко
    0.43
    第一次
    0.43
    addColumn
    0.43
    倝
    0.43
     Wird
    0.42
     ہوج
    0.42
     Aufnahme
    0.42
    POSITIVE LOGITS
    '
    0.54
     servici
    0.51
     servis
    0.50
     services
    0.49
     cmap
    0.48
     தேவ
    0.48
     sarà
    0.47
    लोक
    0.47
    el
    0.47
    ку
    0.47
    Activations Density 0.000%

    No Known Activations