© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126057
    Prev
    Next
    INDEX
    Explanations

    closing quotes and code delimiters

    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_37_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
     python
    0.38
    නි
    0.37
     новую
    0.36
    andas
    0.36
     diferentes
    0.36
     mécanique
    0.36
     desay
    0.36
    税
    0.36
    resher
    0.35
     intr
    0.35
    POSITIVE LOGITS
    契約
    0.40
    ಾಗಿ
    0.39
     goal
    0.39
    productList
    0.38
     상품
    0.37
    Exercises
    0.37
     Stanley
    0.37
    Коммента
    0.37
     살
    0.36
     Mä
    0.36
    Activations Density 0.001%

    No Known Activations