© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136008
    Prev
    Next
    INDEX
    Explanations

    colormap names

    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_12_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
    Health
    0.34
    AM
    0.32
    jakarta
    0.30
    are
    0.29
    OL
    0.29
    Light
    0.29
    light
    0.29
    I
    0.29
    Ht
    0.29
    Priority
    0.28
    POSITIVE LOGITS
     MILLER
    0.35
    제의
    0.32
    町の
    0.29
     оде
    0.28
    кован
    0.28
     těž
    0.28
     conceded
    0.28
     prisão
    0.28
    শিকান্ত
    0.28
    퀴
    0.28
    Activations Density 0.001%

    No Known Activations