© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4461
    Prev
    Next
    INDEX
    Explanations

    tarnished silver

    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_40_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
    啼
    0.38
    sav
    0.36
     yě
    0.34
    irsi
    0.34
    ioane
    0.34
    classe
    0.33
    ahin
    0.33
    ucky
    0.33
    '>"+
    0.33
    classes
    0.33
    POSITIVE LOGITS
    古い
    0.66
     wooden
    0.62
     old
    0.59
     small
    0.56
     leather
    0.56
     маленький
    0.54
     Wooden
    0.53
     작은
    0.53
     стари
    0.53
     деревя
    0.53
    Activations Density 0.038%

    No Known Activations