© 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. 90914
    Prev
    Next
    INDEX
    Explanations

    getting things in order

    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
     autoclave
    0.50
     repurchase
    0.49
     répartition
    0.49
     навіть
    0.49
    Nie
    0.48
     المالية
    0.48
     réforme
    0.48
     Й
    0.48
     liberalism
    0.48
     stabilité
    0.47
    POSITIVE LOGITS
    are
    0.75
    teo
    0.64
    gal
    0.57
    duino
    0.57
    ।
    0.56
    andingan
    0.56
    л
    0.56
    ru
    0.55
    isan
    0.55
    tesy
    0.54
    Activations Density 0.000%

    No Known Activations