© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 99705
    Prev
    Next
    INDEX
    Explanations

    preference

    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_14_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
    kien
    0.18
     أقل
    0.18
    俯
    0.18
    book
    0.18
    物的
    0.18
    مون
    0.17
    ავი
    0.17
    ung
    0.17
    ía
    0.17
    ított
    0.16
    POSITIVE LOGITS
     essere
    0.22
     i
    0.22
     ସ
    0.22
     indir
    0.21
    ER
    0.20
     IND
    0.20
     İ
    0.20
     раздел
    0.20
     IN
    0.20
     である
    0.20
    Activations Density 0.011%

    No Known Activations