© 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. 2516
    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
    ný
    0.76
    ㅋ
    0.72
    𝑦
    0.71
    tenance
    0.70
     sewer
    0.69
    स्थ
    0.69
    䇢
    0.68
    𝒶
    0.68
    nrow
    0.66
    یسم
    0.65
    POSITIVE LOGITS
    un
    0.78
    quoise
    0.72
    মা
    0.71
    precio
    0.70
    ovo
    0.70
    ים
    0.69
    ో
    0.67
    сь
    0.66
    xen
    0.66
    раи
    0.62
    Activations Density 0.137%

    No Known Activations