© 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. 134215
    Prev
    Next
    INDEX
    Explanations

    Specific names/links

    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
     D
    0.47
    //"
    0.44
     kill
    0.42
     Set
    0.41
     Clemens
    0.41
     Tore
    0.40
     CBL
    0.40
    程
    0.40
     Isaac
    0.39
     भोग
    0.39
    POSITIVE LOGITS
    RIE
    0.39
    aham
    0.38
    ώ
    0.38
    綢
    0.38
    取締役
    0.37
    畋
    0.37
    രിക
    0.36
    بيه
    0.36
    మీ
    0.35
    ជំ
    0.35
    Activations Density 0.003%

    No Known Activations