© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91670
    Prev
    Next
    INDEX
    Explanations

    hexadecimal sequences

    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_11_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
    á
    0.59
     personal
    0.53
     Cómo
    0.52
    чками
    0.51
    ert
    0.50
     Вам
    0.49
     получите
    0.49
    ong
    0.49
     sucesivamente
    0.48
     वैर
    0.48
    POSITIVE LOGITS
    {
    0.55
    ἴ
    0.55
    February
    0.51
    Hin
    0.51
    November
    0.50
    没有
    0.49
    硖
    0.49
    March
    0.48
    December
    0.48
    ،
    0.48
    Activations Density 0.017%

    No Known Activations