© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49798
    Prev
    Next
    INDEX
    Explanations

    systems

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     иметь
    0.40
    чему
    0.40
    ভোগ
    0.39
     Từ
    0.39
     सेटिंग
    0.38
    矮
    0.38
    acheter
    0.37
     낮은
    0.37
    দানের
    0.37
    Highest
    0.36
    POSITIVE LOGITS
     proven
    0.41
     fenn
    0.39
    yce
    0.37
     denn
    0.37
     pup
    0.37
     normal
    0.36
     போட்ட
    0.36
    actos
    0.36
    ួល
    0.36
    ɖ
    0.36
    Activations Density 0.002%

    No Known Activations