© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62320
    Prev
    Next
    INDEX
    Explanations

    German compound words, especially with 'Zeug'

    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_2_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
    is
    2.03
    t
    1.76
    to
    1.72
     as
    1.58
    s
    1.45
    are
    1.40
    то
    1.38
    ра
    1.33
    m
    1.23
    는
    1.22
    POSITIVE LOGITS
    T
    0.86
    Sh
    0.83
    ice
    0.80
    ClassName
    0.80
     FMT
    0.80
     ihop
    0.80
    ňuje
    0.80
    ik
    0.79
    ).
    0.79
    ("")
    0.79
    Activations Density 0.003%

    No Known Activations