© 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. 3431
    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
    quela
    3.77
    quele
    2.92
    त
    2.92
    at
    2.89
     PartialEq
    2.87
    ا
    2.84
    з
    2.77
     damn
    2.68
    ᅨ
    2.67
    itories
    2.61
    POSITIVE LOGITS
    ি
    3.15
    ی
    3.07
    রা
    2.91
    egraphics
    2.83
     kojima
    2.77
    দেবের
    2.77
    नुसार
    2.77
    𝘁
    2.76
    此之外
    2.72
    şil
    2.68
    Activations Density 0.038%

    No Known Activations