© 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. 36262
    Prev
    Next
    INDEX
    Explanations

    Look for

    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
     bilgi
    0.62
     g
    0.59
     gooey
    0.59
     a
    0.58
     so
    0.58
     nhưng
    0.58
     mavi
    0.58
     विज्ञान
    0.57
     વિશ્વ
    0.57
     qīng
    0.57
    POSITIVE LOGITS
    Wheat
    0.58
    )。
    0.54
    囑
    0.53
    ﹍
    0.53
    一直
    0.52
     аген
    0.52
    їз
    0.52
    const
    0.51
    )!=
    0.51
    valores
    0.51
    Activations Density 0.006%

    No Known Activations