© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58507
    Prev
    Next
    INDEX
    Explanations

    het + completion

    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
    你去
    0.59
    بوع
    0.56
     líqu
    0.56
     fug
    0.55
    ↵↵
    0.55
     hydroxyl
    0.54
     fouls
    0.54
     kum
    0.53
    ’
    0.53
     reson
    0.52
    POSITIVE LOGITS
    and
    0.73
    0
    0.68
    ending
    0.66
    5
    0.62
    ZA
    0.61
     stesso
    0.60
    4
    0.60
    8
    0.59
    asked
    0.57
    IA
    0.57
    Activations Density 0.000%

    No Known Activations