© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88927
    Prev
    Next
    INDEX
    Explanations

    PET, LD, polymers, plastics, terephthalic

    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_11_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
    ing
    0.50
    en
    0.45
    ar
    0.44
    bulb
    0.44
     Julie
    0.43
    ac
    0.42
     D
    0.42
    ளின்
    0.42
    ard
    0.42
    :
    0.41
    POSITIVE LOGITS
     অপে
    0.48
    О
    0.46
     tempList
    0.45
    ]，
    0.45
    ږ
    0.44
    Ｏ
    0.44
     这
    0.43
    澈
    0.43
     líquido
    0.42
    ]。
    0.42
    Activations Density 0.026%

    No Known Activations