© 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. 87825
    Prev
    Next
    INDEX
    Explanations

    Chinese place name fragments

    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
     Latina
    0.76
    =\
    0.66
     vocals
    0.63
    /
    0.63
    ists
    0.60
     rats
    0.59
     halides
    0.59
    \"");
    0.59
    一层
    0.59
     denominators
    0.57
    POSITIVE LOGITS
    n
    1.19
    nél
    0.96
    nál
    0.83
    ną
    0.82
    ્સ
    0.82
    nw
    0.75
    ﺮ
    0.73
    a
    0.72
    ný
    0.71
    ів
    0.70
    Activations Density 0.005%

    No Known Activations