© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 246
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ../../
    1.14
    en
    0.91
     kuna
    0.86
    ول
    0.84
    которые
    0.83
     unsolicited
    0.81
     defaultdict
    0.80
     convolutional
    0.79
    ంచి
    0.78
    с
    0.78
    POSITIVE LOGITS
    ى
    0.89
    
    0.86
    𝗦
    0.85
    enschaft
    0.85
    𝑔
    0.80
    ños
    0.78
    ोत्तम
    0.76
    INION
    0.74
    ER
    0.74
    zhu
    0.74
    Activations Density 0.020%

    No Known Activations