© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2518
    Prev
    Next
    INDEX
    Explanations

    apartments

    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_39_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
     لس
    0.38
    rocyte
    0.36
    刹
    0.36
     مرگ
    0.36
    OnOff
    0.35
     बाजारों
    0.35
     prépuce
    0.35
     Sitt
    0.35
     actionMode
    0.34
     ރ
    0.34
    POSITIVE LOGITS
     luminos
    0.43
     plot
    0.38
     jardim
    0.37
     jardin
    0.37
     jardín
    0.37
     kind
    0.36
     sal
    0.36
    పూ
    0.36
     terraces
    0.35
    plot
    0.35
    Activations Density 0.017%

    No Known Activations