© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35032
    Prev
    Next
    INDEX
    Explanations

    calling people or famous artists

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    1.01
    s
    0.82
    p
    0.77
    c
    0.76
    stä
    0.73
    de
    0.73
    k
    0.73
    l
    0.72
    set
    0.72
    na
    0.70
    POSITIVE LOGITS
     বিখ্যাত
    0.62
     Ceux
    0.59
    챱
    0.58
     유명
    0.57
     ハン
    0.56
     প্রসিদ্ধ
    0.55
     publiques
    0.55
    {//
    0.55
    hung
    0.54
    ostante
    0.54
    Activations Density 0.036%

    No Known Activations