© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59551
    Prev
    Next
    INDEX
    Explanations

    verses numbers

    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
    это
    0.46
    ความ
    0.45
     this
    0.44
     (
    0.44
     time
    0.44
    时间
    0.42
    เวลา
    0.41
     be
    0.41
    ເຮັດ
    0.41
     melakukan
    0.40
    POSITIVE LOGITS
    owitz
    0.52
    ogliamo
    0.50
    стів
    0.50
    <unused336>
    0.50
    vieve
    0.48
    <unused201>
    0.48
    ccncc
    0.48
     хоче
    0.48
     correctes
    0.46
    ς
    0.46
    Activations Density 0.001%

    No Known Activations