© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61778
    Prev
    Next
    INDEX
    Explanations

    wave or drift

    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_11_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
    어
    0.77
     kwaliteit
    0.71
     incênd
    0.71
     eten
    0.68
    전
    0.68
     o
    0.66
     varia
    0.66
     erken
    0.65
     augmenter
    0.65
     airbags
    0.64
    POSITIVE LOGITS
    с
    0.75
    Wage
    0.69
    ти
    0.65
    closer
    0.65
    ceptible
    0.63
    ்க்க
    0.62
     Сьогодні
    0.62
    Religion
    0.62
    VENTION
    0.62
    cumin
    0.62
    Activations Density 0.002%

    No Known Activations