© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196593
    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_4_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
     on
    0.59
    y
    0.59
     membutuhkan
    0.55
    g
    0.55
    {
    0.55
    _
    0.55
    os
    0.54
    fors
    0.53
    isn
    0.52
    ?
    0.52
    POSITIVE LOGITS
    striatis
    0.65
    ĭ
    0.64
    я
    0.64
     clás
    0.63
    ლებიც
    0.62
     पारिवार
    0.61
    મ
    0.61
    ൽ
    0.60
    드
    0.60
     sparsim
    0.58
    Activations Density 0.000%

    No Known Activations