© 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. 24940
    Prev
    Next
    INDEX
    Explanations

    Increasingly popular

    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
    گو
    0.60
    یت
    0.59
    یں
    0.57
    جہ
    0.56
     اسرائیل
    0.56
    چ
    0.56
    щая
    0.55
     کمپیو
    0.55
    pstmt
    0.55
    みると
    0.55
    POSITIVE LOGITS
     the
    0.70
     која
    0.68
    the
    0.66
     hrá
    0.64
     في
    0.55
     يا
    0.54
     he
    0.54
     a
    0.52
     مكان
    0.52
    verkehr
    0.52
    Activations Density 0.000%

    No Known Activations