© 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. 57328
    Prev
    Next
    INDEX
    Explanations

    introducing examples

    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
    實
    0.54
     summit
    0.52
     stelle
    0.52
    ↵
    0.52
     erst
    0.51
     sum
    0.51
     colon
    0.50
     Plummer
    0.50
    Dataset
    0.50
    ліза
    0.49
    POSITIVE LOGITS
    ،
    0.91
    ၊
    0.77
    ot
    0.76
     품질
    0.75
    ítani
    0.72
    respon
    0.70
    )،
    0.70
     ہیں۔
    0.69
    íticos
    0.68
    ᱔
    0.66
    Activations Density 0.003%

    No Known Activations