© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29368
    Prev
    Next
    INDEX
    Explanations

    id:

    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_10_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
    :
    0.79
     τρόπο
    0.71
    方式
    0.70
    atan
    0.67
     I
    0.66
    ı
    0.65
     રીતે
    0.64
    ഡ്
    0.63
     прочита
    0.63
     نے
    0.63
    POSITIVE LOGITS
     as
    0.74
    s
    0.71
    S
    0.69
    en
    0.67
    너지
    0.66
    斯的
    0.63
    ตร์
    0.63
     Emissions
    0.63
    리
    0.61
    すすめ
    0.60
    Activations Density 0.012%

    No Known Activations