© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39781
    Prev
    Next
    INDEX
    Explanations

    environment

    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
    ي
    0.61
     operar
    0.59
     criminally
    0.56
    الى
    0.55
     traiter
    0.55
     roster
    0.55
     flange
    0.55
     znacz
    0.54
     doPost
    0.54
     avoir
    0.54
    POSITIVE LOGITS
    Time
    0.73
    ed
    0.66
     Zaman
    0.60
     Time
    0.59
    T
    0.59
     E
    0.59
     T
    0.58
     Hanya
    0.57
     Č
    0.57
     Use
    0.55
    Activations Density 0.001%

    No Known Activations