© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 3660
    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
    ि
    3.16
    𝓈
    3.14
    ش
    2.93
    й
    2.89
    ত্ব
    2.86
    ння
    2.81
    べき
    2.80
    िवा
    2.75
     enige
    2.64
    ен
    2.55
    POSITIVE LOGITS
    ب
    3.31
    
    3.25
    
    3.11
    
    3.02
    $>$
    2.81
    
    2.80
    ﺪ
    2.72
    లో
    2.72
     insisting
    2.70
    Tela
    2.70
    Activations Density 0.060%

    No Known Activations