© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60860
    Prev
    Next
    INDEX
    Explanations

    recommended suggestions

    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_11_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
    馕
    0.71
    يل
    0.70
    ون
    0.66
    ב
    0.65
    ה
    0.64
    wijk
    0.63
    wj
    0.62
    ي
    0.62
     Antennes
    0.61
    wem
    0.61
    POSITIVE LOGITS
    ,
    0.60
    다
    0.58
     brewing
    0.57
     gearing
    0.56
     is
    0.55
     hammering
    0.55
     crystallization
    0.54
    ed
    0.53
    |
    0.52
     time
    0.52
    Activations Density 0.011%

    No Known Activations