© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207765
    Prev
    Next
    INDEX
    Explanations

    common names

    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_20_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
    MF
    0.39
    旻
    0.38
    Problem
    0.38
    oteur
    0.38
     আলোকিত
    0.37
    Forge
    0.37
     minors
    0.37
    ittha
    0.37
     problem
    0.37
     nascost
    0.37
    POSITIVE LOGITS
     ප්‍රති
    0.46
    ški
    0.44
    蛋白
    0.44
    骞
    0.44
     handleDelete
    0.42
     setEmail
    0.42
     thereupon
    0.41
     leveraged
    0.40
     уведом
    0.40
     दृढ़
    0.40
    Activations Density 0.001%

    No Known Activations