© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 208119
    Prev
    Next
    INDEX
    Explanations

    hashtags or symbols

    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_56_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
    茶
    0.92
     茶
    0.83
     tea
    0.78
    Tea
    0.76
     Tea
    0.67
     чай
    0.67
    白
    0.64
     白
    0.63
     siy
    0.63
     kah
    0.62
    POSITIVE LOGITS
     '#
    1.13
     "#
    1.13
    "#
    1.09
    ('#
    1.04
    ("#
    0.98
    ="#
    0.97
     `#
    0.94
    :#
    0.91
    :'#
    0.89
     #
    0.89
    Activations Density 0.000%

    No Known Activations