© 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. 91429
    Prev
    Next
    INDEX
    Explanations

    Star, river, gods, kitchen, fox

    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
    s
    1.04
    v
    0.92
    '
    0.92
    em
    0.80
    is
    0.77
    o
    0.75
    ри
    0.71
    t
    0.71
    -
    0.71
    d
    0.69
    POSITIVE LOGITS
     două
    0.68
     kimia
    0.62
     toată
    0.61
     ។
    0.59
     saç
    0.59
     awọn
    0.59
    ∗</
    0.59
    сюда
    0.58
    트를
    0.58
     tranquill
    0.58
    Activations Density 0.001%

    No Known Activations