© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148922
    Prev
    Next
    INDEX
    Explanations

    future tense markers

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    '
    0.69
    不過
    0.44
    '%
    0.44
    '}$
    0.42
    不过
    0.42
     您
    0.40
     noi
    0.39
     maka
    0.39
    ’
    0.39
    ibas
    0.38
    POSITIVE LOGITS
    จะมี
    0.61
     avrà
    0.59
     tendrá
    0.52
    还会
    0.52
    并
    0.51
    會在
    0.51
    会の
    0.50
     будет
    0.50
    会将
    0.50
    会有
    0.50
    Activations Density 0.001%

    No Known Activations