© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 220419
    Prev
    Next
    INDEX
    Explanations

    salutation

    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_10_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
    â
    0.55
     Poland
    0.54
     Кан
    0.54
    ettin
    0.54
    im
    0.52
    immagine
    0.51
    am
    0.50
    ett
    0.50
     #:
    0.50
    ach
    0.50
    POSITIVE LOGITS
     concatenated
    0.50
     divalent
    0.47
     backbone
    0.47
     hội
    0.46
     bús
    0.45
    装着
    0.45
    矢量
    0.45
    元素
    0.45
    ）。
    0.44
     shrunk
    0.44
    Activations Density 0.000%

    No Known Activations