© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1410
    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
    ђа
    2.20
    quela
    2.13
    ä
    2.12
     Molecules
    2.01
    ারের
    1.97
    quele
    1.95
     ina
    1.93
    ert
    1.92
    an
    1.88
    ியை
    1.88
    POSITIVE LOGITS
    ی
    3.05
    ν
    2.71
    ت
    2.62
    ি
    2.30
    se
    2.26
    té
    2.14
    ことになる
    2.10
    tram
    2.07
     gaskets
    2.04
    wolves
    2.04
    Activations Density 0.001%

    No Known Activations