© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8528
    Prev
    Next
    INDEX
    Explanations

    comfortable with

    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_13_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
    运维
    0.49
     ಉ
    0.48
     נישט
    0.47
    Corr
    0.46
     contributo
    0.46
     Contribute
    0.46
    Macro
    0.45
    Slope
    0.44
     뒷
    0.44
     dehumid
    0.44
    POSITIVE LOGITS
    <0x93>
    0.63
    ad
    0.57
    <0x99>
    0.57
    b
    0.54
    اد
    0.50
    сия
    0.50
     kom
    0.48
    minsize
    0.47
     Procter
    0.47
    使用
    0.47
    Activations Density 0.102%

    No Known Activations