© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199100
    Prev
    Next
    INDEX
    Explanations

    Lee, chart, Davies

    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_12_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
    s
    0.71
     육
    0.49
     "'";
    0.49
    ihad
    0.48
     vattati
    0.48
    成为了
    0.48
     ASF
    0.48
    蓣
    0.47
     kháng
    0.46
    加入了
    0.46
    POSITIVE LOGITS
    ров
    0.62
     Davies
    0.55
    ках
    0.52
    sets
    0.51
    рова
    0.50
     Quelle
    0.50
    ሯ
    0.50
    Davies
    0.49
    èdes
    0.49
     Davis
    0.47
    Activations Density 0.002%

    No Known Activations