© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207390
    Prev
    Next
    INDEX
    Explanations

    trillion dollar figures

    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
    可用
    0.47
     powerAll
    0.45
    Hour
    0.44
    比如說
    0.44
    𝗣
    0.44
    அ
    0.44
    giờ
    0.42
    낙
    0.42
    M
    0.42
     Может
    0.42
    POSITIVE LOGITS
     measure
    0.50
     lately
    0.46
    openhagen
    0.46
     trademark
    0.43
    arza
    0.43
     preventative
    0.42
     protest
    0.42
     performance
    0.42
     performances
    0.41
     Liberia
    0.41
    Activations Density 0.001%

    No Known Activations