© 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. 46369
    Prev
    Next
    INDEX
    Explanations

    court rules and rulings

    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
    ation
    0.78
    m
    0.77
    ching
    0.68
    rations
    0.68
    ier
    0.66
    affe
    0.65
    piry
    0.63
    大
    0.63
    ight
    0.62
    oc
    0.61
    POSITIVE LOGITS
    ।
    0.91
    ת
    0.83
    ।”
    0.72
    ।’
    0.72
     wszystkie
    0.71
    。</
    0.71
     oryginal
    0.70
    Ä
    0.70
    ון
    0.69
    Т
    0.69
    Activations Density 0.002%

    No Known Activations