© 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
    2. Gemma-3-27B-IT
    3. 15-GEMMASCOPE-2-TRANSCODER-262K
    4. 17002
    Prev
    Next
    INDEX
    Explanations

    patterns related to "Bean" in contexts like Spring framework configurations. It often predicts words associated with object creation or defining components.**Thinking Process:**1. **Analyze `MAX_ACTIVATING_TOKENS`**: The dominant token is "Bean" (and its variations "bean", "Beans"). "Configuration" and "fixtures" are also present. This strongly suggests the

    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
     ಅಥವಾ
    0.57
     кеңсеси
    0.55
     ಕಂಪ
    0.54
    。.
    0.54
     мае
    0.54
    Ꮫ
    0.52
     ውስ
    0.52
    сия
    0.52
     অপে
    0.52
     ወይም
    0.52
    POSITIVE LOGITS
    le
    0.73
    on
    0.65
    L
    0.64
    Work
    0.63
     Work
    0.59
    ow
    0.58
    ol
    0.57
    ole
    0.55
    werk
    0.55
    et
    0.55
    Activations Density 0.000%

    No Known Activations