© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42847
    Prev
    Next
    INDEX
    Explanations

    New Roman, between passes

    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
    ы
    0.73
     FOUR
    0.68
     breeds
    0.66
    IL
    0.65
     quiere
    0.62
     అయిన
    0.62
     cae
    0.61
     améli
    0.60
     œufs
    0.60
     işle
    0.60
    POSITIVE LOGITS
    ل
    0.98
    ip
    0.68
    wrapper
    0.64
    ル
    0.64
    ic
    0.61
    dataset
    0.61
    کرو
    0.61
    ல்
    0.60
    ጨማሪ
    0.59
    л
    0.58
    Activations Density 0.017%

    No Known Activations