© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7144
    Prev
    Next
    INDEX
    Explanations

    self-driving cars

    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
    y
    2.72
    ن
    2.45
    ು
    2.41
    zelfde
    2.20
    tedir
    2.06
    çok
    1.99
    en
    1.97
    %";
    1.97
    eqa
    1.92
    
    1.88
    POSITIVE LOGITS
    я
    2.16
    これで
    1.89
    ъ
    1.89
    handleClick
    1.86
    ج
    1.85
    ाइ
    1.82
    ри
    1.79
    انه
    1.77
    actually
    1.75
     stacked
    1.74
    Activations Density 0.029%

    No Known Activations