© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13896
    Prev
    Next
    INDEX
    Explanations

    STAAR quiz questions

    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_40_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
     readers
    0.71
     reader
    0.70
     чита
    0.69
    reader
    0.68
    読んで
    0.67
    読
    0.67
     lettura
    0.66
    Readers
    0.66
     readership
    0.66
    읽
    0.64
    POSITIVE LOGITS
    adari
    0.37
    ប៉
    0.37
    ጎ
    0.37
     टो
    0.35
     deco
    0.35
     entered
    0.35
    table
    0.34
    backpack
    0.34
    ポー
    0.34
    ជ្ជ
    0.33
    Activations Density 0.017%

    No Known Activations