© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 45717
    Prev
    Next
    INDEX
    Explanations

    injecting knowledge or trainable parameters

    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_10_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
    s
    0.91
    ere
    0.78
    VE
    0.78
    w
    0.77
    Lin
    0.73
    permission
    0.71
    ampaikan
    0.71
    concern
    0.71
    eri
    0.70
    LL
    0.70
    POSITIVE LOGITS
    ம்
    0.86
    й
    0.79
     inject
    0.76
     injecting
    0.75
    注入
    0.75
     injected
    0.74
     imaged
    0.74
     detalhes
    0.71
     продуктов
    0.71
     productos
    0.70
    Activations Density 0.016%

    No Known Activations