© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20976
    Prev
    Next
    INDEX
    Explanations

    wood

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    animate
    0.38
    aktion
    0.38
    ర్జ
    0.36
     सभ
    0.34
    vapor
    0.34
    acycline
    0.34
    渣
    0.33
    omia
    0.33
     പൂർ
    0.33
    mobile
    0.32
    POSITIVE LOGITS
     Wood
    2.00
    Wood
    1.98
     wood
    1.87
    木
    1.80
     WOOD
    1.73
     woodwork
    1.66
     목
    1.52
     Woody
    1.51
     木
    1.49
    목
    1.49
    Activations Density 0.012%

    No Known Activations