© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37094
    Prev
    Next
    INDEX
    Explanations

    national animal cruelty conservatism

    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
     are
    0.66
    지는
    0.64
     bicarbon
    0.63
     insulating
    0.61
     inclination
    0.61
     isometry
    0.59
    (
    0.59
     advis
    0.58
     economists
    0.58
     medulla
    0.57
    POSITIVE LOGITS
    ية
    0.79
    ه
    0.79
    b
    0.76
    к
    0.75
    اني
    0.73
    f
    0.72
    ur
    0.69
    ني
    0.67
    انات
    0.67
    ד
    0.67
    Activations Density 0.001%

    No Known Activations