© 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. 3597
    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
    й
    2.70
    ⎡
    2.62
    िक
    2.60
    ને
    2.52
    д
    2.45
     основе
    2.39
     convolutions
    2.37
     officials
    2.36
    धात
    2.30
    ==============]
    2.29
    POSITIVE LOGITS
     Decide
    2.93
     fid
    2.59
    岖
    2.58
    ра
    2.42
     мозга
    2.40
    aac
    2.35
    nout
    2.27
     publicit
    2.24
    rj
    2.23
    lightbox
    2.17
    Activations Density 0.001%

    No Known Activations