© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45907
    Prev
    Next
    INDEX
    Explanations

    oil, sebum, growth factor, glands

    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_13_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
    ر
    0.55
    !);
    0.49
    pèce
    0.49
    ㅍ
    0.49
    etimes
    0.47
    pples
    0.46
    >);
    0.46
    ｲ
    0.46
    ratulations
    0.45
    Ｐ
    0.45
    POSITIVE LOGITS
     knitted
    0.49
     qua
    0.41
    '
    0.41
     Mittwoch
    0.40
    चि
    0.40
     linea
    0.40
    <start_of_image>
    0.40
    Controller
    0.39
     llamar
    0.39
     split
    0.38
    Activations Density 0.011%

    No Known Activations