© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27168
    Prev
    Next
    INDEX
    Explanations

    wooden objects

    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
    h
    0.77
     fontWeight
    0.56
    این
    0.52
    ᐅ
    0.51
     شرکت
    0.50
    0
    0.50
     cahaya
    0.49
    ’
    0.49
     Delgado
    0.48
    Código
    0.48
    POSITIVE LOGITS
     wooden
    0.82
     hardwood
    0.81
    wooden
    0.77
     wood
    0.76
    木
    0.75
     dř
    0.71
    ไม้
    0.68
     Wooden
    0.68
     деревя
    0.66
     timber
    0.66
    Activations Density 0.009%

    No Known Activations