© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37050
    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_3_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
     Paths
    0.74
     Origins
    0.74
     Disorders
    0.69
     Markers
    0.69
     Ö
    0.68
    ği
    0.66
     Particles
    0.65
     Makers
    0.65
     Hiring
    0.65
     Mistakes
    0.65
    POSITIVE LOGITS
    ต
    0.88
    ad
    0.87
    ر
    0.83
    تان
    0.82
    ร
    0.81
    ре
    0.75
    تين
    0.75
    ق
    0.75
    ла
    0.74
    ان
    0.71
    Activations Density 0.000%

    No Known Activations