© 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. 123826
    Prev
    Next
    INDEX
    Explanations

    African cities and countries

    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_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
    ต์
    0.66
    ého
    0.65
    ির
    0.51
     тогда
    0.51
    이었
    0.51
     inscriptions
    0.51
     ч
    0.50
    ית
    0.50
    sche
    0.50
    the
    0.50
    POSITIVE LOGITS
     Investigación
    0.62
    い
    0.62
    か月
    0.57
     morto
    0.56
     মিঃ
    0.54
     to
    0.54
     Scoop
    0.53
     Performance
    0.52
    MRT
    0.52
    Policies
    0.52
    Activations Density 0.001%

    No Known Activations