© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13698
    Prev
    Next
    INDEX
    Explanations

    intel cpu generations or specific models

    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_13_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
     A
    0.46
    jahtera
    0.45
    urre
    0.43
    ลล์
    0.43
     versucht
    0.42
    Utc
    0.42
    ピソード
    0.42
    ضه
    0.41
    ి
    0.41
    hofer
    0.41
    POSITIVE LOGITS
    “(
    0.50
    赋予
    0.47
    capitalize
    0.45
    "<<
    0.45
    趵
    0.45
    ၆
    0.44
     sevent
    0.44
     glist
    0.44
    **(
    0.44
     کاس
    0.44
    Activations Density 0.023%

    No Known Activations