© 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-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86322
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_width_262k_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
    f
    0.54
    าย
    0.49
    timed
    0.46
    するのが
    0.46
    res
    0.45
    correlated
    0.45
     greater
    0.43
    an
    0.43
    anik
    0.43
    tables
    0.42
    POSITIVE LOGITS
    न्द
    0.52
    整備
    0.52
     fiducia
    0.50
    𝒖
    0.48
     existencia
    0.47
     contened
    0.46
    路
    0.46
    Ви
    0.46
    फेर
    0.46
     largura
    0.46
    Activations Density 0.000%

    No Known Activations