© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10198
    Prev
    Next
    INDEX
    Explanations

    tags like #

    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_13_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
    <0x0D>
    0.65
    With
    0.57
    Before
    0.57
    🧜
    0.53
     Ocean
    0.52
    ocean
    0.52
    ജെ
    0.51
     बिफोर
    0.51
     seaw
    0.51
     seawater
    0.50
    POSITIVE LOGITS
    ﺮ
    0.53
     обстоя
    0.51
     fragmentary
    0.51
    awiają
    0.50
     rezult
    0.50
     sytu
    0.49
     frug
    0.49
    rza
    0.49
     została
    0.48
    льд
    0.48
    Activations Density 0.019%

    No Known Activations