© 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. 38031
    Prev
    Next
    INDEX
    Explanations

    common sentence starters

    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
     netted
    0.52
    मारक
    0.52
     Manny
    0.51
     आयोजित
    0.51
     copi
    0.51
    aarr
    0.50
    妍
    0.50
     небольшой
    0.50
    áról
    0.48
     পুষ
    0.47
    POSITIVE LOGITS
    _
    0.58
     imperatives
    0.57
    z
    0.57
    l
    0.57
    en
    0.56
    et
    0.56
    la
    0.55
    lib
    0.55
    ла
    0.54
    n
    0.53
    Activations Density 0.002%

    No Known Activations