© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58704
    Prev
    Next
    INDEX
    Explanations

    él como

    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
    有助于
    0.61
    া
    0.56
    ссов
    0.55
    `);
    0.55
    غا
    0.55
    瑷
    0.52
     écl
    0.51
     épa
    0.51
    llan
    0.50
    㑨
    0.49
    POSITIVE LOGITS
    is
    0.76
    '
    0.63
     government
    0.60
     पुरानी
    0.60
    water
    0.59
     body
    0.58
     پانی
    0.58
     ಜನರು
    0.57
    isches
    0.57
     जाम
    0.56
    Activations Density 0.007%

    No Known Activations