© 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. 35755
    Prev
    Next
    INDEX
    Explanations

    Eurovision Song Contest winner

    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
    '
    0.88
    驄
    0.61
    t
    0.61
     shreds
    0.55
     shells
    0.54
    ק
    0.54
    ด
    0.51
     cruel
    0.50
    #'
    0.50
     out
    0.49
    POSITIVE LOGITS
    umann
    0.62
     Couldn
    0.62
     Neumann
    0.60
     Lembrando
    0.59
     也
    0.57
    phyll
    0.57
    洧
    0.57
     pourra
    0.56
    ра
    0.56
    ppard
    0.55
    Activations Density 0.000%

    No Known Activations