© 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. 53493
    Prev
    Next
    INDEX
    Explanations

    3

    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
     sport
    0.40
     half
    0.37
    >→</
    0.36
     {(
    0.35
    পূর্বক
    0.35
     fist
    0.35
    বাসী
    0.34
     गर्व
    0.34
    galaxys
    0.34
    
    0.34
    POSITIVE LOGITS
     long
    0.59
    long
    0.54
     longa
    0.54
     LONG
    0.51
    Long
    0.49
     लॉन्ग
    0.48
     Long
    0.48
     дъл
    0.45
    4
    0.45
     довго
    0.45
    Activations Density 0.005%

    No Known Activations