© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202215
    Prev
    Next
    INDEX
    Explanations

    prime ideals

    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_12_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
    gak
    0.57
    begin
    0.54
    promote
    0.53
     Verlag
    0.51
    dependent
    0.50
    grammar
    0.49
    작
    0.49
    pivot
    0.48
    ibraries
    0.48
    ágot
    0.48
    POSITIVE LOGITS
    ির
    0.66
     Blade
    0.63
     tungsten
    0.62
     comida
    0.59
     Cinco
    0.55
     sende
    0.54
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.53
     würden
    0.53
     tequila
    0.53
     DRAM
    0.53
    Activations Density 0.000%

    No Known Activations