© 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. 86350
    Prev
    Next
    INDEX
    Explanations

    futurism, ism, Qu, arism

    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
    কে
    0.92
    이지만
    0.88
    나
    0.82
    이었다
    0.80
    দের
    0.80
    та
    0.78
    이랑
    0.75
    ক
    0.73
    นี้
    0.73
     jeopard
    0.73
    POSITIVE LOGITS
    s
    0.80
    IA
    0.70
     Padres
    0.65
    äck
    0.63
     Nonprofit
    0.62
    h
    0.61
    agent
    0.61
    ่า
    0.59
     Mechanical
    0.58
    fade
    0.57
    Activations Density 0.001%

    No Known Activations