© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 213768
    Prev
    Next
    INDEX
    Explanations

    avoid redundancy

    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_43_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
     redundant
    1.96
     redundancy
    1.95
    redund
    1.87
     redund
    1.77
     redundancies
    1.65
    冗
    1.49
    Red
    1.01
     Red
    0.95
     made
    0.92
    made
    0.89
    POSITIVE LOGITS
     Viitattu
    0.38
    kehr
    0.38
     واقف
    0.37
    thebetter
    0.37
    歙
    0.37
    ris
    0.36
    ély
    0.36
     सिविल
    0.36
     gil
    0.36
     scrot
    0.36
    Activations Density 0.023%

    No Known Activations