© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 236038
    Prev
    Next
    INDEX
    Explanations

    gardening

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    oger
    0.38
     Kochubei
    0.36
    unitary
    0.36
     विरोधी
    0.35
     Pauli
    0.35
    პ
    0.35
     separable
    0.34
    蜜
    0.34
    ituary
    0.33
    ลับ
    0.33
    POSITIVE LOGITS
    阮
    0.42
    љено
    0.41
     rulers
    0.40
     strategy
    0.40
    ด้าน
    0.39
    Porsche
    0.39
    margins
    0.38
    苹
    0.38
    Пор
    0.37
     Printed
    0.37
    Activations Density 0.001%

    No Known Activations