© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78145
    Prev
    Next
    INDEX
    Explanations

    football world cup winners

    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_29_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
    onyl
    0.39
     نسبت
    0.39
     अधिवेशन
    0.38
    센
    0.38
     بیش
    0.36
     مقابل
    0.36
     cốt
    0.36
    ozer
    0.36
    চাই
    0.36
     ಅಂತ
    0.36
    POSITIVE LOGITS
     sind
    0.43
     telecoms
    0.39
     Magde
    0.38
     destes
    0.38
     seves
    0.38
     islands
    0.38
     („
    0.38
     Islands
    0.38
     (=
    0.38
     troph
    0.37
    Activations Density 0.008%

    No Known Activations