© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25836
    Prev
    Next
    INDEX
    Explanations

    roots of rooted trees

    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_10_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
    '
    0.83
    t
    0.75
    _
    0.65
    .
    0.65
    l
    0.61
     Bonds
    0.59
     fundo
    0.59
    
    0.59
     Message
    0.58
     as
    0.57
    POSITIVE LOGITS
    adakan
    0.62
    atino
    0.55
     multiplicado
    0.54
     blanchâtre
    0.54
    ること
    0.53
    ukannya
    0.53
    kanı
    0.53
    ertype
    0.53
     bằng
    0.52
    ột
    0.52
    Activations Density 0.000%

    No Known Activations