© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 90037
    Prev
    Next
    INDEX
    Explanations

    EncodeError, ModelingLanguage

    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_3_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
    고
    0.69
    лл
    0.68
    Задача
    0.67
    २
    0.65
    >[</
    0.64
     ReturnVal
    0.63
    Ņ
    0.62
    (
    0.62
     Dương
    0.61
    的方向
    0.61
    POSITIVE LOGITS
    fice
    0.80
     for
    0.71
     forbidden
    0.68
     it
    0.67
    f
    0.66
    fors
    0.64
     puisse
    0.64
    ু
    0.64
     l
    0.61
     practicable
    0.61
    Activations Density 0.001%

    No Known Activations