© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83001
    Prev
    Next
    INDEX
    Explanations

    nortriptyline HCl

    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_0_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
    с
    1.23
     to
    1.09
     are
    1.02
     on
    0.96
     (
    0.90
    ьте
    0.89
    ail
    0.86
     is
    0.84
    getPosition
    0.83
     $
    0.81
    POSITIVE LOGITS
    ي
    2.13
    ת
    1.84
    ة
    1.76
    ר
    1.71
    ন
    1.62
    م
    1.62
    י
    1.58
    न
    1.53
    ী
    1.52
    ت
    1.51
    Activations Density 0.000%

    No Known Activations