© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 197536
    Prev
    Next
    INDEX
    Explanations

    density vs weight

    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_27_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
     restraining
    0.37
    PPS
    0.37
     главных
    0.36
     उपरोक्त
    0.36
     When
    0.35
    斻
    0.35
     MyBatis
    0.35
    ECs
    0.34
     Glove
    0.34
     denotes
    0.33
    POSITIVE LOGITS
    소년
    0.39
    انية
    0.36
    ສົ່ງ
    0.36
    嗉
    0.36
    ຟ
    0.36
     Georg
    0.35
    ร้อม
    0.35
    zości
    0.34
    فرج
    0.34
    yson
    0.34
    Activations Density 0.014%

    No Known Activations