© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 126539
    Prev
    Next
    INDEX
    Explanations

    customization and scripting

    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_37_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
    试
    0.42
     trial
    0.42
    試
    0.41
     Trial
    0.39
     unwa
    0.39
    émico
    0.38
    día
    0.38
    
    0.38
    klich
    0.37
    Trial
    0.37
    POSITIVE LOGITS
     custom
    0.70
     customizations
    0.65
    custom
    0.64
     Custom
    0.61
     customization
    0.61
    Custom
    0.59
     customized
    0.59
    developed
    0.59
    定制
    0.58
     Customized
    0.57
    Activations Density 0.209%

    No Known Activations