© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221270
    Prev
    Next
    INDEX
    Explanations

    frequency, damping, release

    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_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     seated
    0.42
     raising
    0.40
     awake
    0.40
     Tibetan
    0.40
     physiotherapy
    0.39
     Lond
    0.37
     congratulations
    0.37
    ('/')
    0.37
     hiking
    0.36
     hospitalized
    0.36
    POSITIVE LOGITS
     проце
    0.41
    charCodeAt
    0.41
    芥
    0.41
    ҷи
    0.39
    elabor
    0.39
     ইস্য
    0.38
     dân
    0.37
    羸
    0.37
     Шу
    0.37
     metaf
    0.36
    Activations Density 0.032%

    No Known Activations