© 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. 3438
    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
    те
    2.37
    ر
    2.13
    й
    2.00
    er
    1.87
    ᴄ
    1.84
     phép
    1.72
    скай
    1.68
    িক
    1.68
    йки
    1.62
    besar
    1.61
    POSITIVE LOGITS
     hassle
    2.17
    ed
    2.08
     публикации
    2.06
     diphtheria
    2.01
    ة
    2.00
    ₪
    2.00
    ्या
    1.97
    artige
    1.96
    aidl
    1.91
    δος
    1.89
    Activations Density 0.004%

    No Known Activations