© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46055
    Prev
    Next
    INDEX
    Explanations

    random number generator seeding

    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
     is
    0.87
    ра
    0.81
     in
    0.75
    at
    0.73
    は
    0.73
    จะ
    0.71
    ка
    0.68
    的
    0.68
    ol
    0.68
    ה
    0.68
    POSITIVE LOGITS
    л
    0.82
     conflitto
    0.81
     fortemente
    0.77
     amplio
    0.73
    지는
    0.72
     variété
    0.71
     атмосфер
    0.70
    ー
    0.69
    ີ
    0.69
     carc
    0.68
    Activations Density 0.011%

    No Known Activations