© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48886
    Prev
    Next
    INDEX
    Explanations

    sink elements consuming data

    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
     caldera
    0.83
     volcan
    0.79
    ],
    0.77
    ),
    0.74
    )،
    0.72
     המ
    0.69
     ativa
    0.66
     ס
    0.65
     adicional
    0.65
     библиотека
    0.65
    POSITIVE LOGITS
    to
    1.10
    то
    0.90
    ار
    0.89
    。</
    0.85
    。
    0.82
    as
    0.82
    де
    0.81
    ارو
    0.79
    ต์
    0.78
    the
    0.74
    Activations Density 0.001%

    No Known Activations