© 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. 36580
    Prev
    Next
    INDEX
    Explanations

    like phrase

    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
    ح
    0.78
    人
    0.73
     \%
    0.69
     It
    0.66
     \
    0.63
    ار
    0.57
    re
    0.57
     \#
    0.57
    رض
    0.56
     $$\
    0.56
    POSITIVE LOGITS
    ك
    0.86
    ة
    0.79
    er
    0.71
     zwischen
    0.69
    ",
    0.66
    ው
    0.64
    υ
    0.63
     thị
    0.61
    ка
    0.61
     elke
    0.61
    Activations Density 0.028%

    No Known Activations