© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7554
    Prev
    Next
    INDEX
    Explanations

    neural activity and plasticity

    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_39_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
     radiations
    0.40
    偻
    0.39
    睾
    0.39
    Radiation
    0.38
     infar
    0.38
     neurolog
    0.38
     radiation
    0.37
    飴
    0.37
     Radiation
    0.37
    казыва
    0.36
    POSITIVE LOGITS
    pot
    0.49
    enie
    0.44
    exc
    0.42
    inh
    0.41
    rette
    0.40
     Exc
    0.39
     Recruitment
    0.38
    gain
    0.38
    Firing
    0.38
    ography
    0.36
    Activations Density 0.074%

    No Known Activations