© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30817
    Prev
    Next
    INDEX
    Explanations

    built-in

    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_7_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
    ч
    0.78
    и
    0.78
    ре
    0.77
    사와
    0.73
    ری
    0.73
    зи
    0.71
    סי
    0.71
    н
    0.71
    дя
    0.70
    TrackedDevice
    0.70
    POSITIVE LOGITS
    s
    1.17
    t
    1.13
     be
    1.05
    o
    0.91
    oš
    0.89
    os
    0.82
    telling
    0.79
     not
    0.76
    ant
    0.76
    3
    0.74
    Activations Density 0.013%

    No Known Activations