© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204105
    Prev
    Next
    INDEX
    Explanations

    path 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_25_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
     refug
    0.35
     usos
    0.35
    форм
    0.33
     F
    0.33
     calving
    0.33
     brukes
    0.33
     obecnie
    0.33
     strewn
    0.33
     sia
    0.32
    الت
    0.32
    POSITIVE LOGITS
    ProductID
    0.41
     ချ
    0.40
    ']==
    0.39
    chtigt
    0.39
    诚信
    0.38
     године
    0.38
    kfollowers
    0.38
    marshalN
    0.38
     सेले
    0.38
    ವಾದ
    0.38
    Activations Density 0.000%

    No Known Activations