© 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. 89722
    Prev
    Next
    INDEX
    Explanations

    headings

    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
     o
    0.73
    o
    0.70
    l
    0.65
     você
    0.59
    you
    0.58
    resources
    0.57
    ob
    0.57
    database
    0.56
    ।
    0.55
    。
    0.55
    POSITIVE LOGITS
     ERISA
    0.54
     ordination
    0.52
    ETHOD
    0.50
     ablation
    0.48
    ждении
    0.47
    νονται
    0.46
    INER
    0.46
     REI
    0.46
     axonal
    0.46
     ERC
    0.45
    Activations Density 0.004%

    No Known Activations