© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199067
    Prev
    Next
    INDEX
    Explanations

    photo contest submission feedback

    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_27_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
    裵
    0.29
     Microscope
    0.28
    这座
    0.28
     Oliva
    0.28
    穷
    0.28
    Datos
    0.28
     листь
    0.27
     Shallow
    0.27
     Olson
    0.27
    大多数
    0.27
    POSITIVE LOGITS
     marchand
    0.29
    ISTAN
    0.29
    膻
    0.29
     শব্দের
    0.29
     erbjuder
    0.29
     обеспечить
    0.29
     подчи
    0.28
     gifted
    0.28
     '-'
    0.28
     beton
    0.28
    Activations Density 0.001%

    No Known Activations