© 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-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18953
    Prev
    Next
    INDEX
    Explanations

    gradient mathematical operator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_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
    pt
    0.66
    year
    0.51
    ak
    0.51
    nd
    0.50
    irt
    0.50
     ->
    0.50
    v
    0.50
    要
    0.49
    am
    0.49
     =>
    0.49
    POSITIVE LOGITS
     Kähler
    0.61
    FullScreen
    0.59
     জলাবদ্ধ
    0.55
     salón
    0.52
     protección
    0.51
     Acción
    0.51
     searchQuery
    0.51
     María
    0.50
     সক্ষম
    0.50
     Clubhouse
    0.50
    Activations Density 0.004%

    No Known Activations