© 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. 3454
    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
    ির
    1.78
    ن
    1.72
    ج
    1.54
    ह
    1.51
    fice
    1.50
    NCIA
    1.47
    ка
    1.47
     viene
    1.46
    ف
    1.46
    ेल
    1.44
    POSITIVE LOGITS
    +}$
    2.03
     prerequisite
    1.89
    𝑑
    1.82
     busy
    1.71
    𝑟
    1.70
    𝑛
    1.70
     fledgling
    1.69
    scre
    1.68
    +}
    1.67
    ς
    1.66
    Activations Density 0.063%

    No Known Activations