© 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
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60184
    Prev
    Next
    INDEX
    Explanations

    i.e

    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_11_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
    textepsilon
    0.68
     imasmim
    0.66
     可愛い
    0.65
    🍱
    0.64
     Такие
    0.64
    toadd
    0.64
    setcounter
    0.63
    downcase
    0.62
     fantástico
    0.62
    🥛
    0.62
    POSITIVE LOGITS
    on
    0.65
    k
    0.59
    Sp
    0.58
     of
    0.58
     is
    0.57
    -
    0.57
    """
    0.55
     The
    0.54
    一
    0.54
     on
    0.53
    Activations Density 0.003%

    No Known Activations