© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32728
    Prev
    Next
    INDEX
    Explanations

    quoted speech indicators

    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
    くなった
    0.41
    водство
    0.38
     applying
    0.36
     }},
    0.34
     comenzó
    0.34
     raggiunto
    0.34
     quiet
    0.34
    接続
    0.34
     Tugas
    0.34
    gua
    0.33
    POSITIVE LOGITS
    berkeley
    0.38
     Бей
    0.35
     कोणत्या
    0.35
    通貨
    0.35
    逭
    0.35
     автором
    0.34
     الإنسان
    0.33
     dieu
    0.33
    怎么
    0.33
     hoạch
    0.33
    Activations Density 0.004%

    No Known Activations