© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88527
    Prev
    Next
    INDEX
    Explanations

    authors' names

    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_3_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
    ל
    0.79
    ล
    0.77
    י
    0.68
     DRM
    0.67
    ἐ
    0.67
     aval
    0.66
    ية
    0.65
     esche
    0.64
     ergibt
    0.64
     kern
    0.62
    POSITIVE LOGITS
    S
    0.90
    t
    0.78
    T
    0.77
    matching
    0.74
    glacial
    0.71
    neurons
    0.69
    L
    0.69
    writing
    0.68
    costs
    0.68
    dioxide
    0.68
    Activations Density 0.003%

    No Known Activations