© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31558
    Prev
    Next
    INDEX
    Explanations

    pull, tear, or rotating motion

    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_31_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
    洷
    0.44
     baked
    0.41
     caustic
    0.39
     contamin
    0.39
    newTask
    0.39
    Calcium
    0.38
    Cartoon
    0.38
    Pract
    0.37
    Monthly
    0.37
     excesses
    0.37
    POSITIVE LOGITS
    旋转
    0.44
     effective
    0.39
    biome
    0.39
     दाब
    0.39
    輪
    0.39
     effetto
    0.39
     rotating
    0.39
     effektiv
    0.39
    ဖြေ
    0.39
    эф
    0.38
    Activations Density 0.101%

    No Known Activations