© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44681
    Prev
    Next
    INDEX
    Explanations

    Microsoft Windows XP

    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_3_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
     of
    0.75
     in
    0.71
     WHICH
    0.69
    在
    0.68
    am
    0.64
    ла
    0.64
    al
    0.61
    ii
    0.59
    壹章
    0.59
    ༧
    0.58
    POSITIVE LOGITS
    ع
    0.79
    خ
    0.69
    其他
    0.69
    时候
    0.67
    یی
    0.64
    acchati
    0.64
    ید
    0.63
    ط
    0.63
    ali
    0.61
    onn
    0.61
    Activations Density 0.002%

    No Known Activations