© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19216
    Prev
    Next
    INDEX
    Explanations

    nuclear association, garbage collection

    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_15_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
    Nas
    0.58
    X
    0.57
    K
    0.57
    j
    0.56
    i
    0.52
    F
    0.50
    After
    0.50
    咖啡
    0.50
    Chocolate
    0.49
    after
    0.49
    POSITIVE LOGITS
     acheté
    0.54
     WARRANTY
    0.51
     singleton
    0.51
     interrupts
    0.50
     écriv
    0.50
     grounds
    0.49
     LABEL
    0.49
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.48
     tweets
    0.48
     realized
    0.48
    Activations Density 0.000%

    No Known Activations