© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61862
    Prev
    Next
    INDEX
    Explanations

    multilingual instructions

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    （
    0.76
    (
    0.69
     (‘
    0.69
     (!
    0.68
     (“
    0.68
    !',
    0.66
    (\
    0.63
     ($\
    0.63
     („
    0.63
    POSITIVE LOGITS
     understand
    0.47
     hiểu
    0.41
     understanding
    0.39
     people
    0.38
     fcc
    0.38
    เข้าใจ
    0.38
     verstehen
    0.38
     사람
    0.37
     quỹ
    0.37
     ob
    0.37
    Activations Density 0.000%

    No Known Activations