© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36588
    Prev
    Next
    INDEX
    Explanations

    nature of existence

    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_11_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
     anonymously
    0.59
     anunciar
    0.59
     trivially
    0.57
    𝘷
    0.57
     indicar
    0.53
    образной
    0.53
     elevados
    0.53
     ouvrir
    0.53
    ⸨
    0.53
     visant
    0.52
    POSITIVE LOGITS
    ara
    0.61
    aga
    0.57
    ha
    0.56
    isten
    0.55
    serie
    0.53
    ida
    0.52
    ām
    0.52
     gyroscope
    0.52
     gypsy
    0.51
    gy
    0.50
    Activations Density 0.007%

    No Known Activations