© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136510
    Prev
    Next
    INDEX
    Explanations

    street names and suffixes

    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_12_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
    are
    0.54
     k
    0.49
    lices
    0.49
     spruce
    0.47
     c
    0.46
    bukkit
    0.46
     replacing
    0.46
     keys
    0.46
    ork
    0.45
    bble
    0.45
    POSITIVE LOGITS
     saludable
    0.51
     Уда
    0.50
    שי
    0.46
     Zhuang
    0.46
     saludables
    0.45
     Пан
    0.45
     []:
    0.45
    INSTDIR
    0.44
    جي
    0.44
    ULONG
    0.44
    Activations Density 0.000%

    No Known Activations