© 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. 36659
    Prev
    Next
    INDEX
    Explanations

    South Park and Australia

    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
    t
    0.88
    il
    0.78
    y
    0.75
    ين
    0.74
     in
    0.74
     encourage
    0.74
    ar
    0.71
     The
    0.69
     decid
    0.68
     understand
    0.66
    POSITIVE LOGITS
    Fs
    0.77
     joueurs
    0.73
     phận
    0.71
    cwd
    0.71
    valmentaja
    0.70
    ጅም
    0.68
    личество
    0.67
    stations
    0.66
    qualiter
    0.66
    ⑮
    0.65
    Activations Density 0.001%

    No Known Activations