© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35958
    Prev
    Next
    INDEX
    Explanations

    how many people

    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
    刚
    0.54
    <0x80>
    0.52
    spoken
    0.52
     at
    0.51
    ну
    0.50
    还有
    0.50
     to
    0.49
    专用
    0.49
    写法
    0.49
    дія
    0.49
    POSITIVE LOGITS
     மே
    0.61
     Beasts
    0.58
     वर्ल्ड
    0.57
    壑
    0.56
     एक्सच
    0.54
    нд
    0.53
     wedges
    0.52
     bowlers
    0.52
     ම
    0.52
    Alpine
    0.51
    Activations Density 0.001%

    No Known Activations