© 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. 126910
    Prev
    Next
    INDEX
    Explanations

    agent-based simulation, modeling, architectures, execution

    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
    ו
    0.85
    0.81
    {
    0.76
    \%
    0.64
    <0xAF>
    0.61
    \
    0.60
     orice
    0.59
    0.57
     awfully
    0.54
    滨
    0.54
    POSITIVE LOGITS
    ال
    0.86
    ▥
    0.85
     who
    0.79
     there
    0.75
    ل
    0.75
     Jerman
    0.74
     for
    0.71
    ُوا
    0.70
    unitary
    0.69
    detector
    0.68
    Activations Density 0.001%

    No Known Activations