© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18273
    Prev
    Next
    INDEX
    Explanations

    rice types and preparation

    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_15_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
     quartiers
    0.55
     abbastanza
    0.54
    },"
    0.54
    আমার
    0.52
     میرے
    0.52
     sketchbook
    0.52
    equalToSuperview
    0.51
     சிற்ப
    0.50
    astanza
    0.50
     অস্ত
    0.49
    POSITIVE LOGITS
     сме
    0.58
     שמ
    0.48
    ंदोल
    0.47
    を受
    0.46
    (
    0.45
    スマ
    0.45
     شن
    0.45
     আগমন
    0.45
    ד
    0.45
     timely
    0.44
    Activations Density 0.001%

    No Known Activations