© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172417
    Prev
    Next
    INDEX
    Explanations

    column headers

    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_20_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
    úng
    0.21
     AVAILABLE
    0.20
    *;
    0.19
    ><
    0.19
     există
    0.18
    در
    0.18
    开
    0.17
    win
    0.17
    >{
    0.17
    readystatechange
    0.17
    POSITIVE LOGITS
    izzazione
    0.22
     traveler
    0.20
     Towns
    0.19
    今後の
    0.19
    hebung
    0.19
    ো
    0.18
    tabPage
    0.18
     mani
    0.18
     nour
    0.18
    Mes
    0.18
    Activations Density 0.003%

    No Known Activations