© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130355
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or digits

    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_6_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
    are
    0.95
     =>
    0.93
     {
    0.92
     =
    0.86
     ->
    0.85
     +=
    0.84
     >
    0.82
    ،
    0.82
     or
    0.82
    yla
    0.78
    POSITIVE LOGITS
    한
    1.20
    พ
    1.05
    ض
    0.99
    िंग
    0.94
    ة
    0.93
    로
    0.93
    টি
    0.89
    ін
    0.89
    드
    0.88
    лся
    0.88
    Activations Density 0.000%

    No Known Activations