© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37295
    Prev
    Next
    INDEX
    Explanations

    well-known and lesser-known

    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_11_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
    login
    0.66
    وت
    0.65
    l
    0.65
    rawn
    0.63
    asty
    0.63
    о
    0.61
    larni
    0.60
    لف
    0.59
    monitoring
    0.59
    notifications
    0.59
    POSITIVE LOGITS
     Auger
    0.59
     Católica
    0.59
     deceive
    0.57
    瑷
    0.57
    ↵
    0.55
     alakalı
    0.55
     subjectivity
    0.54
     forgo
    0.54
     shov
    0.54
    ed
    0.54
    Activations Density 0.002%

    No Known Activations