© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108102
    Prev
    Next
    INDEX
    Explanations

    Meniere's disease, meningitis

    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_2_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
    5
    1.41
    ation
    1.16
    ك
    1.13
    8
    1.12
    4
    1.05
    した
    1.02
    for
    1.02
    ط
    1.01
    1
    1.00
    اق
    0.99
    POSITIVE LOGITS
    ي
    1.09
    ,
    1.07
    ższ
    1.02
    i
    0.99
    ಿ
    0.99
    ිය
    0.93
     QSOs
    0.93
    在
    0.88
    to
    0.86
     objected
    0.85
    Activations Density 0.000%

    No Known Activations