© 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. 129652
    Prev
    Next
    INDEX
    Explanations

    modify

    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
    ';"
    0.41
     ܠ
    0.39
    甶
    0.37
     предпринима
    0.36
    स्तू
    0.36
    禣
    0.35
    noop
    0.35
    boundingRect
    0.35
    MaxPool
    0.35
    ilan
    0.35
    POSITIVE LOGITS
    тера
    0.42
     Ter
    0.41
    inkle
    0.40
     teasing
    0.39
    ᴴ
    0.39
     Ters
    0.39
     breat
    0.38
    anky
    0.38
    вают
    0.38
     etmektedir
    0.38
    Activations Density 0.002%

    No Known Activations