© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1615
    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
    s
    1.09
    specialchars
    1.02
    가
    0.97
    ের
    0.96
    
    0.89
    
    0.89
    
    0.87
    setShow
    0.87
    violet
    0.86
    helix
    0.85
    POSITIVE LOGITS
    ہ
    1.03
    ان
    0.98
    نا
    0.94
    рни
    0.89
    𝘢
    0.88
    वर
    0.85
    𝘰
    0.83
    ં
    0.83
    িক
    0.82
    ות
    0.81
    Activations Density 0.204%

    No Known Activations