© 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. 89471
    Prev
    Next
    INDEX
    Explanations

    open space and Canada

    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
     gacchati
    0.64
    accès
    0.63
    𝚎
    0.61
    のは
    0.61
     médiocrement
    0.60
     транспо
    0.60
     ಯಾವಾಗ
    0.59
    ので
    0.59
    鑑定
    0.59
     noastră
    0.58
    POSITIVE LOGITS
    k
    1.17
    z
    1.01
    us
    0.94
    c
    0.94
    ai
    0.91
    is
    0.90
    ल
    0.85
    od
    0.83
     has
    0.83
    st
    0.83
    Activations Density 0.000%

    No Known Activations