© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257597
    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
    cantidad
    0.99
    अगर
    0.98
    OwnProperty
    0.95
     bisa
    0.94
    گفت
    0.93
    ی
    0.92
    calculated
    0.92
    boundary
    0.92
     yarg
    0.92
    cyt
    0.91
    POSITIVE LOGITS
     MBE
    0.93
     μεταξύ
    0.88
    াসহ
    0.87
    ู
    0.87
    UART
    0.85
     lato
    0.84
    碍
    0.83
     Bilbao
    0.83
    තික
    0.83
     lockers
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.