© 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. 90218
    Prev
    Next
    INDEX
    Explanations

    well

    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
    nten
    0.71
    asını
    0.71
    дцать
    0.67
     overturned
    0.66
     hierv
    0.65
     fouled
    0.64
    uradaki
    0.63
    ﺔ
    0.63
    letos
    0.62
     Бүгенге
    0.62
    POSITIVE LOGITS
    0.78
    for
    0.57
    OK
    0.56
    อ
    0.55
     高
    0.54
    Generation
    0.53
    <0x85>
    0.51
    ท
    0.51
     }
    0.49
     for
    0.49
    Activations Density 0.001%

    No Known Activations