© 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. 43918
    Prev
    Next
    INDEX
    Explanations

    blackbird, blackwood, blackwater, beans, bird, water

    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
    .
    0.69
    CAD
    0.64
    :
    0.64
     restaur
    0.64
    er
    0.62
    তার
    0.61
    ।
    0.61
    2
    0.60
    ir
    0.60
     RGB
    0.59
    POSITIVE LOGITS
    ى
    0.70
    ۹
    0.66
    המ
    0.65
    effect
    0.61
    הר
    0.61
    အရေ
    0.60
     بی‌
    0.60
    м
    0.58
    ۳
    0.58
    προ
    0.57
    Activations Density 0.002%

    No Known Activations