© 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. 57122
    Prev
    Next
    INDEX
    Explanations

    much + comparative

    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
    는
    0.63
    是
    0.62
    the
    0.61
    ast
    0.61
    rick
    0.57
    icar
    0.55
    洷
    0.55
    icot
    0.54
    体现
    0.54
    h
    0.54
    POSITIVE LOGITS
    м
    0.90
    م
    0.83
    ва
    0.63
     bande
    0.63
    ור
    0.62
     fuses
    0.62
     Dienste
    0.61
     vuurp
    0.59
    село
    0.58
    archiwizowane
    0.58
    Activations Density 0.009%

    No Known Activations