© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35932
    Prev
    Next
    INDEX
    Explanations

    ' and 'addition' followed by a comma or 'if'

    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
     മിക
    0.47
     taxation
    0.45
    ب
    0.43
    retirement
    0.42
     retirement
    0.42
    وس
    0.42
    になる
    0.42
    ഹ്ലാ
    0.41
     innovation
    0.41
     endure
    0.41
    POSITIVE LOGITS
    ByName
    0.45
     c
    0.43
    ى
    0.41
     Хан
    0.41
    TaskPojo
    0.41
     координаты
    0.41
     Пар
    0.40
     definiert
    0.37
     Те
    0.37
     почти
    0.37
    Activations Density 0.002%

    No Known Activations