© 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. 45031
    Prev
    Next
    INDEX
    Explanations

    boils down to

    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
    0.93
     t
    0.84
     l
    0.69
    т
    0.68
     Alzheimer
    0.67
     n
    0.65
    ONG
    0.64
     in
    0.64
    д
    0.64
    RING
    0.63
    POSITIVE LOGITS
     aument
    0.73
    a
    0.71
    ა
    0.71
    for
    0.69
    šću
    0.69
     distribu
    0.68
     encont
    0.68
     reuni
    0.67
    ുള്ള
    0.65
    čnom
    0.65
    Activations Density 0.018%

    No Known Activations