© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197666
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    StatusInternal
    0.43
     descubrimiento
    0.38
     lowers
    0.38
     devenit
    0.38
     виде
    0.37
     divent
    0.37
    visao
    0.37
    鐘
    0.37
    auen
    0.37
    acoli
    0.37
    POSITIVE LOGITS
     satisfying
    0.48
    satisfied
    0.45
     satisfied
    0.43
    滿足
    0.42
     satisfy
    0.41
     удовле
    0.40
    
    0.40
     Satisfaction
    0.39
     подчер
    0.39
     satisf
    0.38
    Activations Density 0.008%

    No Known Activations