© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 131002
    Prev
    Next
    INDEX
    Explanations

    t-words

    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_6_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
    ۵
    0.81
    ۹
    0.80
    ید
    0.77
    ۳
    0.73
    Don
    0.72
    Tanggal
    0.71
    Begriff
    0.70
    {
    0.70
    ۴
    0.69
    ৫
    0.68
    POSITIVE LOGITS
    er
    0.94
    ul
    0.75
    ри
    0.75
    य़ा
    0.72
    eres
    0.70
     వచ్చిన
    0.69
    ners
    0.67
    erde
    0.65
    um
    0.64
    য়
    0.64
    Activations Density 0.002%

    No Known Activations