© 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
    2. Gemma-3-4B-IT
    3. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 259586
    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_10_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
    ı
    1.18
     li
    0.99
    ık
    0.96
    ので
    0.95
    li
    0.94
    ır
    0.93
     prova
    0.93
     weiteren
    0.92
    util
    0.92
    pt
    0.89
    POSITIVE LOGITS
     encirc
    1.35
    RAEL
    1.34
     affliction
    1.33
     Uhuru
    1.31
    $(".
    1.29
     MSM
    1.28
     eigenvectors
    1.28
     afflict
    1.26
     lucrative
    1.25
    
    1.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.