© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217525
    Prev
    Next
    INDEX
    Explanations

    word fragments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    тьяна
    0.42
    тья
    0.41
    Station
    0.37
    τιο
    0.36
    ɕ
    0.36
     xiv
    0.36
    сса
    0.35
    !...
    0.35
    Own
    0.34
    խ
    0.34
    POSITIVE LOGITS
     Revol
    0.44
    unud
    0.39
     temper
    0.38
    lemon
    0.38
     Spect
    0.38
    showinfo
    0.37
    levi
    0.37
     Spectre
    0.37
     levi
    0.37
    েইলি
    0.37
    Activations Density 0.000%

    No Known Activations