© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124468
    Prev
    Next
    INDEX
    Explanations

    arcuate uterus

    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
    P
    0.73
    C
    0.66
     enkele
    0.64
    缦
    0.62
    Архи
    0.61
    y
    0.61
     do
    0.60
    妘
    0.60
    滘
    0.60
    B
    0.60
    POSITIVE LOGITS
    ani
    0.82
    ित
    0.69
    ando
    0.66
    är
    0.65
    air
    0.64
    ने
    0.62
    0.62
    2
    0.62
    eli
    0.61
    political
    0.61
    Activations Density 0.000%

    No Known Activations