© 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. 44269
    Prev
    Next
    INDEX
    Explanations

    AntConc, Autopista, Automata, Anticonvulsants, automatic reply

    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
    "
    0.74
    يف
    0.71
    Лю
    0.66
    LAUNCH
    0.59
     nimmt
    0.58
    ก็
    0.57
    Ла
    0.57
    ва
    0.57
     wurde
    0.57
    OPHY
    0.57
    POSITIVE LOGITS
    u
    0.64
    or
    0.64
    presa
    0.64
    s
    0.63
    ay
    0.63
    and
    0.63
    თვის
    0.63
    ुली
    0.63
    shells
    0.61
    系列的
    0.61
    Activations Density 0.005%

    No Known Activations