© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248632
    Prev
    Next
    INDEX
    Explanations

    prefixes for incomplete

    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_56_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
    ත්‍
    0.41
     liv
    0.37
     sello
    0.36
     attribut
    0.35
    لاک
    0.34
    liv
    0.33
     subTest
    0.33
    Ẹ
    0.33
     pä
    0.33
    स्वा
    0.33
    POSITIVE LOGITS
    此之外
    0.71
    evším
    0.67
    oretically
    0.64
    pośred
    0.61
    neath
    0.57
    letzt
    0.57
    mselves
    0.55
    verläss
    0.53
    ตรฐาน
    0.52
    ங்கிணை
    0.52
    Activations Density 0.000%

    No Known Activations