© 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. 51039
    Prev
    Next
    INDEX
    Explanations

    production-ready

    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
    degree
    0.72
    maximize
    0.70
    Mode
    0.69
    knife
    0.69
    </h3>
    0.68
    download
    0.68
    ྥ
    0.68
    necess
    0.66
    stop
    0.65
    computation
    0.65
    POSITIVE LOGITS
     was
    0.96
    רים
    0.80
     were
    0.80
    w
    0.77
     d
    0.77
    দ
    0.77
    ু
    0.75
     said
    0.74
    ר
    0.74
     atras
    0.72
    Activations Density 0.002%

    No Known Activations