© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126755
    Prev
    Next
    INDEX
    Explanations

    Sisyphus, Rossbach, phus

    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_3_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
    ;
    0.66
     има
    0.64
    ა
    0.64
     име
    0.63
     материа
    0.61
    ק
    0.59
    ین
    0.59
     разви
    0.58
    рт
    0.58
    िया
    0.57
    POSITIVE LOGITS
    that
    0.77
    l
    0.62
     Ríos
    0.61
    lar
    0.58
     THAT
    0.57
    ro
    0.55
    که
    0.55
    ril
    0.55
    తో
    0.54
    ან
    0.54
    Activations Density 0.000%

    No Known Activations