© 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. 1593
    Prev
    Next
    INDEX
    Explanations

    window and balcony views

    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
     banane
    0.38
     longitude
    0.36
     bananas
    0.35
     banana
    0.34
     Cushing
    0.34
    苇
    0.34
     ordinairement
    0.33
     срока
    0.32
     grooves
    0.32
    ionych
    0.32
    POSITIVE LOGITS
     balcony
    0.56
     windows
    0.54
    window
    0.51
     lighting
    0.51
     window
    0.50
     WINDOW
    0.50
     jendela
    0.49
    windows
    0.49
     balconies
    0.49
    窓
    0.49
    Activations Density 0.012%

    No Known Activations