© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49668
    Prev
    Next
    INDEX
    Explanations

    code and URLs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
     ਹ
    0.47
     ਜਾਣ
    0.46
     initializing
    0.46
     ਵਿੱਚ
    0.45
     storing
    0.45
     Moscou
    0.45
     မြ
    0.45
     klein
    0.45
     တ
    0.44
     န
    0.44
    POSITIVE LOGITS
     работа
    0.75
     работы
    0.71
     допол
    0.71
     хорошо
    0.63
     еще
    0.62
     сотрудни
    0.61
     путем
    0.61
     также
    0.61
     режи
    0.60
     обра
    0.60
    Activations Density 0.002%

    No Known Activations