© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3032
    Prev
    Next
    INDEX
    Explanations

    background check

    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_39_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
     Brilliant
    0.38
     syllables
    0.38
    翔
    0.36
     brilliant
    0.35
     Liter
    0.35
    ্জ
    0.35
    estrutura
    0.35
    ड्यूल
    0.34
     kaks
    0.34
     വസ്തു
    0.34
    POSITIVE LOGITS
    дии
    0.38
    precio
    0.38
     ফাঁ
    0.38
    penet
    0.36
    rVert
    0.36
    嗜
    0.36
    ເຈ
    0.35
    ައ
    0.34
    obei
    0.34
    教育
    0.34
    Activations Density 0.000%

    No Known Activations