© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 75517
    Prev
    Next
    INDEX
    Explanations

    World Cup winners Brazil

    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_31_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
     моло
    0.38
     dissipation
    0.38
    ხვ
    0.38
    三角
    0.37
     annulus
    0.36
     competing
    0.36
    逋
    0.36
    pathTemplates
    0.35
     ото
    0.35
    োধনী
    0.34
    POSITIVE LOGITS
    soap
    0.40
    []
    0.38
    玺
    0.38
     государственной
    0.37
     స్థితి
    0.36
    肥料
    0.36
    咀
    0.35
    ende
    0.35
     soap
    0.35
    asc
    0.34
    Activations Density 0.001%

    No Known Activations