© 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. 210348
    Prev
    Next
    INDEX
    Explanations

    areas of mathematics

    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
     puțin
    0.42
    ताना
    0.40
     బా
    0.39
    DebugSymbols
    0.39
     lipids
    0.38
    Შ
    0.37
    ंचे
    0.37
     Euras
    0.37
    Დ
    0.37
    Ocean
    0.36
    POSITIVE LOGITS
    ues
    0.50
    clock
    0.48
    cur
    0.46
    ue
    0.45
    ging
    0.45
    kj
    0.45
    yt
    0.44
    cock
    0.44
    unting
    0.43
    millan
    0.43
    Activations Density 0.001%

    No Known Activations