© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61782
    Prev
    Next
    INDEX
    Explanations

    loop constructs and their nesting

    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_11_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
    ”（
    0.56
     tornar
    0.53
     să
    0.52
     decât
    0.52
     modifier
    0.52
    <0x91>
    0.50
     comité
    0.49
     bulletins
    0.49
     accentuate
    0.48
    يسي
    0.48
    POSITIVE LOGITS
    c
    0.61
    ano
    0.54
    id
    0.53
    ac
    0.53
    स्परिक
    0.53
    as
    0.52
    ல்
    0.50
    af
    0.50
    sensitivity
    0.49
    had
    0.49
    Activations Density 0.089%

    No Known Activations