© 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. 90581
    Prev
    Next
    INDEX
    Explanations

    Project Euler, Project Gutenberg

    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
    t
    0.91
    이면
    0.72
    이지만
    0.71
    s
    0.66
    ן
    0.65
     сучас
    0.64
    이기
    0.63
     проект
    0.62
     projective
    0.62
     projection
    0.61
    POSITIVE LOGITS
     be
    0.85
    ру
    0.81
    ET
    0.77
    ية
    0.72
    р
    0.71
    ER
    0.70
    UL
    0.69
    )。
    0.69
    రి
    0.67
    。
    0.67
    Activations Density 0.001%

    No Known Activations