© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176620
    Prev
    Next
    INDEX
    Explanations

    output verb

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ရာ
    0.47
    카오
    0.42
     take
    0.38
    拳
    0.37
     temp
    0.37
     pull
    0.37
    Dynamic
    0.37
    rások
    0.36
    Takes
    0.35
    Johann
    0.35
    POSITIVE LOGITS
     ausz
    0.50
     çık
    0.49
     xuất
    0.49
     vý
    0.48
    vý
    0.46
     sortie
    0.46
     出
    0.45
     çıkan
    0.45
    出る
    0.43
     Vý
    0.41
    Activations Density 0.016%

    No Known Activations