© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24825
    Prev
    Next
    INDEX
    Explanations

    football players and clubs

    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_10_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
    𝙎
    0.70
     воздей
    0.69
     accidentes
    0.69
    ه
    0.68
     prévenir
    0.67
     الذ
    0.64
    了很多
    0.64
     incidences
    0.63
     этом
    0.63
     accidents
    0.63
    POSITIVE LOGITS
    ]
    0.78
     Energy
    0.74
     Company
    0.71
    camp
    0.71
    I
    0.71
    Company
    0.71
     Companies
    0.71
    à
    0.71
    )
    0.70
    connection
    0.69
    Activations Density 0.002%

    No Known Activations