© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 216674
    Prev
    Next
    INDEX
    Explanations

    dance with or after claim

    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_16_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
    0.56
    ו
    0.54
    aa
    0.50
    ha
    0.50
    os
    0.49
    로
    0.47
    的选择
    0.47
    с
    0.47
    vi
    0.46
    ang
    0.46
    POSITIVE LOGITS
     estimating
    0.59
     México
    0.59
     stressors
    0.55
     quieras
    0.55
     mexican
    0.53
     delineate
    0.53
    㮔
    0.52
     calorías
    0.51
    ল্যান্ডের
    0.51
     året
    0.51
    Activations Density 0.000%

    No Known Activations