© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62953
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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_59_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
    するもの
    0.77
    したもの
    0.77
     것
    0.64
    もの
    0.55
    երը
    0.52
    のもの
    0.50
    ները
    0.50
    ものは
    0.49
    টেলে
    0.45
    ը
    0.41
    POSITIVE LOGITS
     آمریک
    0.78
     সঙ্গ
    0.75
     امریک
    0.74
     মাধ্যম
    0.66
    লাই
    0.64
    )')
    0.60
    মাই
    0.59
    চাই
    0.57
    տն
    0.57
     বির
    0.56
    Activations Density 0.004%

    No Known Activations