© 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
    3. Gemma-3-27B-IT
    5. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196555
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    eating
    0.62
    approach
    0.61
    8
    0.61
    ム
    0.60
    coefficient
    0.59
    s
    0.59
    environment
    0.57
    area
    0.56
    dub
    0.56
    genesis
    0.56
    POSITIVE LOGITS
     rápido
    0.54
    uação
    0.50
    ppure
    0.49
     Umfang
    0.48
     journée
    0.47
    iniert
    0.47
    тике
    0.47
    читься
    0.46
    rógeno
    0.46
    䍜
    0.46
    Activations Density 0.000%

    No Known Activations