© 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. 46413
    Prev
    Next
    INDEX
    Explanations

    zoonotic disease and rooibos

    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
    ின்
    0.64
    的市场
    0.64
    ون
    0.62
    َب
    0.61
    的热
    0.60
    ية
    0.59
    了一个
    0.57
    并未
    0.55
    {
    0.55
    纵
    0.55
    POSITIVE LOGITS
    n
    0.96
    p
    0.93
    h
    0.92
    r
    0.87
    on
    0.82
    am
    0.80
    w
    0.76
    i
    0.74
    Road
    0.72
    mz
    0.71
    Activations Density 0.010%

    No Known Activations