© 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. 14345
    Prev
    Next
    INDEX
    Explanations

    nginx configuration blocks

    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
    umping
    0.70
    ió
    0.60
    kei
    0.57
     ı
    0.56
    كتر
    0.55
    ny
    0.54
    ufen
    0.54
    óry
    0.54
    urring
    0.54
     পদার্থ
    0.53
    POSITIVE LOGITS
    Pot
    0.57
     bronchitis
    0.53
    Lond
    0.51
    Დ
    0.51
    PLE
    0.51
    Pog
    0.50
    Ფ
    0.49
     waterways
    0.48
    Გ
    0.48
    ﺏ
    0.48
    Activations Density 0.010%

    No Known Activations