© 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. 88853
    Prev
    Next
    INDEX
    Explanations

    lost

    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
     of
    0.71
    لی
    0.69
    )
    0.68
     ambulatory
    0.65
     médical
    0.64
    ของ
    0.64
    ור
    0.64
    '
    0.64
    اتی
    0.63
    ін
    0.62
    POSITIVE LOGITS
    is
    0.86
    tries
    0.68
    tests
    0.66
    and
    0.61
    箓
    0.61
    Preferred
    0.60
    dött
    0.60
    store
    0.59
    as
    0.59
    form
    0.59
    Activations Density 0.003%

    No Known Activations