© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 195389
    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
     default
    0.50
     solo
    0.49
     redwood
    0.48
     to
    0.48
    ю
    0.48
     background
    0.48
    ，
    0.47
     music
    0.47
     software
    0.47
     tanque
    0.46
    POSITIVE LOGITS
     områ
    0.59
    bewegung
    0.57
     इंपोर्टेंट
    0.56
    pani
    0.55
    <unused291>
    0.55
     እንቅስቃሴ
    0.55
    UIActions
    0.54
     Еўропы
    0.54
    <unused743>
    0.54
    㫴
    0.54
    Activations Density 0.000%

    No Known Activations