© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86787
    Prev
    Next
    INDEX
    Explanations

    records safety or builds reputation

    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_18_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
    桷
    0.59
    かる
    0.48
     JAG
    0.46
     lir
    0.46
    боро
    0.46
     шриф
    0.45
    ликт
    0.45
    риф
    0.45
    ตร์
    0.45
    зда
    0.45
    POSITIVE LOGITS
    ı
    0.51
     metastases
    0.50
     discoveries
    0.48
     produces
    0.48
    ü
    0.48
     authenticity
    0.47
    utian
    0.47
     producción
    0.46
     उत्पादन
    0.46
     metastable
    0.46
    Activations Density 0.000%

    No Known Activations