© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7631
    Prev
    Next
    INDEX
    Explanations

    categorized breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    ра
    0.86
    เหลือ
    0.82
    生素
    0.79
    
    0.78
    ுங்கள்
    0.75
    %>%
    0.74
    fait
    0.73
    vič
    0.70
     desarrolla
    0.68
    getNum
    0.68
    POSITIVE LOGITS
    nata
    0.85
    ن
    0.85
    ন
    0.80
    邯
    0.80
     DataTypes
    0.79
     doctrina
    0.76
    middels
    0.74
    naj
    0.73
     giá
    0.72
    straction
    0.72
    Activations Density 0.048%

    No Known Activations