© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34623
    Prev
    Next
    INDEX
    Explanations

    Rajendra, Prasad, Patel, Rajnikant

    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_3_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
    。
    0.77
    س
    0.76
    સ
    0.75
    is
    0.71
    、
    0.71
    م
    0.70
    ز
    0.64
    )。
    0.59
    れる
    0.59
    タ
    0.58
    POSITIVE LOGITS
     in
    0.60
    an
    0.59
    lash
    0.57
    kinase
    0.54
    ﺄ
    0.52
    ari
    0.52
    amma
    0.52
    AVER
    0.52
    lax
    0.52
    т
    0.52
    Activations Density 0.000%

    No Known Activations