© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53401
    Prev
    Next
    INDEX
    Explanations

    introduction of topics or concepts

    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_31_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
    যায়
    0.39
    沪
    0.39
     jaringan
    0.38
    Currency
    0.36
     beschik
    0.36
    elon
    0.36
     solicitado
    0.35
    ః
    0.35
    滬
    0.35
    ByCategory
    0.34
    POSITIVE LOGITS
     unfamiliar
    0.63
     สำหรับ
    0.57
     unaware
    0.55
     if
    0.55
     Familiar
    0.54
     إذا
    0.50
     For
    0.49
    สำหรับ
    0.49
     nếu
    0.48
     אם
    0.48
    Activations Density 0.165%

    No Known Activations